Christian-Katzmann/pdoom-skills

ملف Christian-Katzmann

آخر نشاط مصدر مسجل: ٨ سبتمبر ٢٠٢٦ في ١٧:٢٠

آخر تحديث لفهرس SkillsMP: ٢٦ أكتوبر ٢٠٢٦ في ١١:٣٧

skills مجمعة: ٤٤

نجوم GitHub: ٠
تفرعات GitHub: ٠

ملف README للمستودع

مصدر ملف README للمستودع: README.md

قراءة الملف الأصلي

عرض ملف README كاملًا

# (p)doom-skills 18 methods and local tools for Codex and Claude Code, selected and adapted by Christian Katzmann to help agents investigate, decide, build and verify. **Status:** Runnable examples and recorded checks are included for all 18 packages. Small model comparisons include ties, mixed results and failed attempts; they do not establish a general success rate. [Browse the website](https://christian-katzmann.github.io/pdoom-skills/) · [Find a skill](#find-a-useful-skill) · [Install one](#install-one-skill) [![Product Walkthrough: the sample app confirms a saved note, but after reload the note field is empty.](design/screenshots/walkthrough-result.png)](packages/product-walkthrough/examples/walkthrough.md) *Product Walkthrough caught a deliberately planted save failure in Pocket List. These are captures from the actual browser run, with synthetic data and partial coverage. [Replay the run](packages/product-walkthrough/examples/walkthrough.md) or [regenerate this image](design/screenshots/render.mjs).* Each skill supplies instructions and, where useful, scripts or references for your coding agent. Read its example and limitations, then install only what fits your work. The website lets you inspect the collection; skills run through your local agent and any tools or services they require. ## Install one skill With Git and Python 3.12 available: ```sh git clone https://github.com/Christian-Katzmann/pdoom-skills.git cd pdoom-skills python3 -m venv .venv .venv/bin/python -m pip install -r tools/requirements.txt ./install list ./install install thinking-hats --host codex --dry-run ./install install thinking-hats --host codex ``` For Claude, replace `--host codex` with `--host claude`. The installer displays dependency requirements, refuses unrelated or edited files, and retains reversible transactions. Use `--dest` to choose the exact skills directory. On macOS, temporary destinations must use resolved paths such as `/private/tmp/`, because `/tmp/` is a symlink. See [installation and reversal](tools/README.md). In Codex, invoke `$thinking-hats` with your actual decision and relevant evidence. For example: `$thinking-hats Review whether this import can safely be retried. Inspect the importer and its tests, identify duplicate-write risks, and propose the smallest useful check.` In Claude, use `/thinking-hats`. Each [package README](packages/thinking-hats/README.md) lists its exact entrypoints, prerequisites and first use. Installation tests verify directory layouts; they do not prove discovery or reasoning quality in every client version. ## Find a useful skill ### Thinking and decisions | Skill | Use it for | | --- | --- | | [Bottleneck](packages/bottleneck/README.md) | Find the limiting business step or the next measurement needed to choose it, without making guesses into proven constraints. | | [Expert Mode](packages/expert-mode/README.md) | Finds the specific specialty a question belongs to, researches only when a named knowledge gap could change the answer, and takes a position with its trade-off. | | [Force Multiplier](packages/force-multiplier/README.md) | Finds a specific change that makes existing assets more useful, with observed drag, an amplification mechanism, the first move and work to stop. | | [Next Moves](packages/next-moves/README.md) | Compares what a product promises with what its repository contains, then names the few capabilities its users would most obviously reach for and not find. | | [Thinking Hats](packages/thinking-hats/README.md) | Chooses one focused reasoning lens before coding, so the lens decides what the agent inspects first, distrusts, writes before coding and verifies. | | [Vision](packages/vision/README.md) | Recovers what a project is actually about from its own history, tells a chosen change of direction apart from unnoticed drift, and tests candidate statements against real decisions including one they should reject. | ### Build and maintain | Skill | Use it for | | --- | --- | | [ADX](packages/adx/README.md) | Give coding agents checked repository commands, verification and recovery, with drift checks and a small-repository path. | | [App It](packages/app-it/README.md) | Make a local web project a macOS app with a native window, managed servers, warm reopen and explicit cleanup. | | [Autoloop](packages/autoloop/README.md) | Plan and run finite local file experiments that measure the original first and retain only guarded improvements in a separate Git repository. | | [Ghost Invasion](packages/ghost-invasion/README.md) | Run seeded browser journeys against a disposable local app and reproduce failures with captured evidence. | | [Kit the Skill](packages/kit-the-skill/README.md) | Decides whether a skill needs supporting files at all, and if so the smallest kind that changes what the agent does, on a ladder from no addition up to executable support. | | [Secrets Rotation](packages/secrets-rotation/README.md) | Rehearse staged credential replacement, consumer reload checks, grace, revocation and recovery with a local fake provider. | ### Presentation and walkthroughs | Skill | Use it for | | --- | --- | | [Product Walkthrough](packages/product-walkthrough/README.md) | Record expectations before acting, expose broken promises in a running product, and validate findings, evidence and honest coverage. | | [Repo Craft](packages/repo-craft/README.md) | Turn repository presentation into useful proof of the actual project, with a portable probe and reproducible terminal visuals. | ### Feedback and improvement | Skill | Use it for | | --- | --- | | [Agent Coach](packages/agent-coach/README.md) | Analyze selected sessions, track applied advice separately, and observe whether its associated problem changes in later comparable sessions. | | [Closed Loop](packages/closed-loop/README.md) | Finds where a measured outcome should change a later action and wires the smallest feedback loop that does it, or says to stay stateless. | | [Health Synthesis](packages/health-synthesis/README.md) | Combine review findings while preserving each ID, recorded verdict and conflict outcome; check coverage and merge consistency. | | [Token Optimizer](packages/token-optimizer/README.md) | Find and repair repeated context, retrieval, caching, tool-definition and retry waste, measuring whole-task behavior before claiming savings. | ## Inspect the evidence - [Repo Craft's Fairshare CLI](packages/repo-craft/examples/walkthrough.md): executed terminal output, repository before and after, and editable image sources. The project is synthetic; the commands ran. - [Product Walkthrough's Pocket List](packages/product-walkthrough/examples/walkthrough.md): a note lost on reload, a passing delete-cancellation check, screenshots and a runnable app. Coverage is deliberately partial. - [Ghost Invasion's double-submit case](packages/ghost-invasion/examples/walkthrough.md): seeded failure, repeat, reduced reproduction and fixed control with browser and database evidence. It needs its bundled engine, a browser and Docker. - [Secrets Rotation's offline tutorial](packages/secrets-rotation/examples/walkthrough.md): setup, two rotations, failed rollout and recovery using only generated fake credentials and a fake provider. - [Vision's repaired comparison](packages/vision/comparison/difficult/evaluation.md): the original difficult result and rerun remain inspectable. Only an authorized decision-maker's approval establishes an intentional pivot. - [Thinking Hats' migration comparison](packages/thinking-hats/comparison/difficult/evaluation.md): narrow additional retirement and rollback decisions. Both answers already catch the main integrity problems; no migration was executed. Each package retains its full comparison record, including unfavorable results and exclusions. The [collection's own Repo Craft report](docs/collection-presentation/report.md) records how this landing page was assembled. ## Verify or build locally ```sh . .venv/bin/activate python3 -B tools/validate_packages.py --packages-root packages --catalog site/catalog.json --release python3 -B tools/verify_release.py cd site npm ci npm run build:release ``` The release check installs and reverses every package in disposable Codex and Claude directories. Package-specific commands and conditions live beside each package. The static site requires Node 22.12 or newer and supports root and project-subpath builds. See [site setup and preview](site/README.md) and the [complete release verification commands](docs/verification.md). ## Reuse and contribute Original collection adaptations use [MIT](LICENSE). [Credits and notices](NOTICE.md) preserve upstream material and acknowledge established methods; the collection does not claim their invention. Dependencies keep their own licenses. Read [support and limitations](SUPPORT.md) and [contribution guidance](CONTRIBUTING.md). No installation command launches a model, configures a paid provider, or deploys the site.

جارٍ تحميل ملف README للمستودع…

Skills في هذا المستودع

المهن الحاسوبية الأخرى مطوّرو البرمجيات متخصصو إدارة المشاريع مديرو الشبكات وأنظمة الحاسوب

٨ فئات مهنية · 100% مصنفة

skill

المهنة

الوصف

آخر تحديث

adx-forensic

مديرو الشبكات وأنظمة الحاسوب

Diagnose wrong setup commands, unclear verification, recovery gaps and stale repository guidance. Use for first-time agent onboarding or an evidence-backed ADX assessment. Includes the executable ADX kit; no companion installation is required.

لغة النص الأصلي: الإنجليزية

2026-09-08

adx-implement

مديرو الشبكات وأنظمة الحاسوب

Make repository setup, verification and recovery executable from observed ADX findings. Use to adopt or repair agent guidance and selected repository contracts. Includes its own kit and inspection/re-audit procedure, with small-repository restraint.

لغة النص الأصلي: الإنجليزية

2026-09-08

adx-re-audit

مديرو الشبكات وأنظمة الحاسوب

Check whether existing repository guidance and ADX commands still match current files. Detect stale paths, invalid contracts, broken verification references and expired claims. Works without a code-index service and includes the entire kit.

لغة النص الأصلي: الإنجليزية

2026-09-08

agent-coach

علماء البيانات

Analyze explicitly selected sessions, record prior advice separately, and check whether its associated problem changes in later comparable sessions.

لغة النص الأصلي: الإنجليزية

2026-09-08

app-it

مطوّرو البرمجيات

Turn a local web project or hosted URL into a macOS Dock-launchable app using bundled Swift/WebKit and shell templates. Use for repeatable build, install, warm server reopen, explicit quit, and port ownership verification.

لغة النص الأصلي: الإنجليزية

2026-09-08

autoloop-planner

مطوّرو البرمجيات

Decide whether a goal supports repeated local measurement, then prepare fixed evaluator, constrained file candidates and a bounded executable Autoloop batch. Use for planning keep-or-discard experiments or rejecting unreliable optimization goals.

لغة النص الأصلي: الإنجليزية

2026-09-08

autoloop

مطوّرو البرمجيات

Run a finite local experiment batch with measured baseline, fixed scorer, bounded work and kept or discarded file changes. Use for prepared measurable file experiments, inspecting results or trying the bundled demo.

لغة النص الأصلي: الإنجليزية

2026-09-08

bottleneck

متخصصو إدارة المشاريع

Identify which business or service step may be limiting completed work, using flow, capacity, queues and demand evidence. Apply the Theory of Constraints focusing steps with provisional alternatives and a next measurement when evidence is incomplete. Use for…

لغة النص الأصلي: الإنجليزية

2026-09-08

closed-loop

مطوّرو البرمجيات

Finds where a measured outcome should change a later action and wires the smallest feedback loop that does it, with the minimum state that carries the signal between runs. Specifies signal, reference, comparator, correction, cadence and governor, then…

لغة النص الأصلي: الإنجليزية

2026-09-08

expert-mode

متخصصو إدارة المشاريع

Find the specific specialty behind a substantive decision, identify missing evidence, research only when it could change the answer, and recommend a position with its trade-off and reversal condition. Use for advice, architecture, design judgment,…

لغة النص الأصلي: الإنجليزية

2026-09-08

force-multiplier

متخصصو إدارة المشاريع

Find what already exists in a situation that could do far more work, and the specific change that would make it do so. Use when the user asks for the highest-leverage move, a force multiplier, an asymmetric advantage, how to do more with less, what they are…

لغة النص الأصلي: الإنجليزية

2026-09-08

ghost-invasion

محللو ضمان جودة البرمجيات والمختبرون

Run seeded browser scenarios against a disposable local app with Ghost Invasion, inspect captured failures, and reproduce bugs. Use for fake-user behavior and small concurrency checks with the bundled, separately installed CLI dependency.

لغة النص الأصلي: الإنجليزية

2026-09-08

health-synthesis

موظفو المكاتب العامون

Combine review findings into one synthesis while preserving every ID, recorded verdict and conflict outcome. Use for reconciling several reviews or checking that a summary has not dropped findings.

لغة النص الأصلي: الإنجليزية

2026-09-08

kit-the-skill

مطوّرو البرمجيات

Decide whether a skill needs supporting files at all, and if so the smallest kind that changes what the agent does. Use when the user asks whether a skill should ship scripts, schemas, fixtures, references or templates, asks to review a skill's companion…

لغة النص الأصلي: الإنجليزية

2026-09-08

next-moves

متخصصو إدارة المشاريع

Finds the next few product improvements a domain expert would expect a software project to have, separates a real missing capability from a deliberate omission, and ranks the survivors by maturity-weighted user value with a deterministic scorer. Use when the…

لغة النص الأصلي: الإنجليزية

2026-09-08

product-walkthrough-audit

محللو ضمان جودة البرمجيات والمختبرون

Walk a running product, record expectations before acting, and report reproduced failures with validated findings and explicit coverage. Use for first-use checks, broken promises, and an evidence-backed product punch list.

لغة النص الأصلي: الإنجليزية

2026-09-08

repo-craft

مطوّرو البرمجيات

Improve a repository's README and presentation using evidence from the actual project, a read-only probe, and three tests for choosing useful artifacts. Use for a repository presentation audit or preparation for publication. Distinguishes repository…

لغة النص الأصلي: الإنجليزية

2026-09-08

secrets-rotation

محللو أنظمة الحاسوب

Create and inspect an isolated secret-rotation simulation with a local fake provider. Use to rehearse staged replacement, consumer reload checks, grace, revocation and recovery without real credentials.

لغة النص الأصلي: الإنجليزية

2026-09-08

thinking-hats

مطوّرو البرمجيات

Choose one focused reasoning lens (a hat) before architecture, refactoring, debugging, reliability, concurrency, data-migration, security, input-boundary, workflow, abstraction, cost, product-systems or verification work, then let that hat decide what to…

لغة النص الأصلي: الإنجليزية

2026-09-08

token-optimizer-forensic

مطوّرو البرمجيات

Find and repair structural token waste in an AI workflow, checking task quality, retries, cost and latency before calling it a win.

لغة النص الأصلي: الإنجليزية

2026-09-08

token-optimizer-implement

مطوّرو البرمجيات

Find and repair structural token waste in an AI workflow, checking task quality, retries, cost and latency before calling it a win.

لغة النص الأصلي: الإنجليزية

2026-09-08

vision

متخصصو إدارة المشاريع

Recover what a project is really about from its own folder and history, and say it plainly enough that a stranger gets it in thirty seconds. Use on "what is this project actually about", "articulate the vision", "north star", "why are we building this", "have…

لغة النص الأصلي: الإنجليزية

2026-09-08

adx-forensic

المهن الحاسوبية الأخرى

Synthetic installation fixture for ADX. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

adx-implement

المهن الحاسوبية الأخرى

Synthetic installation fixture for ADX. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

adx-re-audit

المهن الحاسوبية الأخرى

Synthetic installation fixture for ADX. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

agent-coach

المهن الحاسوبية الأخرى

Synthetic installation fixture for Agent Coach. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

app-it

المهن الحاسوبية الأخرى

Synthetic installation fixture for App It. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

autoloop-planner

المهن الحاسوبية الأخرى

Synthetic installation fixture for Autoloop. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

autoloop

المهن الحاسوبية الأخرى

Synthetic installation fixture for Autoloop. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

bottleneck

المهن الحاسوبية الأخرى

Synthetic installation fixture for Bottleneck. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

closed-loop

المهن الحاسوبية الأخرى

Synthetic installation fixture for Closed Loop. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

expert-mode

المهن الحاسوبية الأخرى

Synthetic installation fixture for Expert Mode. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

force-multiplier

المهن الحاسوبية الأخرى

Synthetic installation fixture for Force Multiplier. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

ghost-invasion

المهن الحاسوبية الأخرى

Synthetic installation fixture for Ghost Invasion. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

health-synthesis

المهن الحاسوبية الأخرى

Synthetic installation fixture for Health Synthesis. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

kit-the-skill

المهن الحاسوبية الأخرى

Synthetic installation fixture for Kit the Skill. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

next-moves

المهن الحاسوبية الأخرى

Synthetic installation fixture for Next Moves. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

product-walkthrough

المهن الحاسوبية الأخرى

Synthetic installation fixture for Product Walkthrough. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

repo-craft

المهن الحاسوبية الأخرى

Synthetic installation fixture for Repo Craft. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

secrets-rotation

المهن الحاسوبية الأخرى

Synthetic installation fixture for Secrets Rotation. Use only to exercise collection tooling.

لغة النص الأصلي: الإنجليزية

2026-09-08

عرض ٤٠ من أصل ٤٤ skills مجمعة.

التثبيت بمساعدة مساعد ذكي

انسخ هذا الطلب إلى المساعد الذكي الذي تستخدمه.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/Christian-Katzmann/pdoom-skills.