Menu
SkillsMP has collected 27 skills from adihebbalae/Attacca. Open a skill to review its source and details.
Showing 27 of 27 collected skills.
Pressure-tests a built feature, PR, or design against multiple independent, no-context skeptical personas through iterative rounds of objection and rebuttal, until every fixable objection is actually fixed and only genuine values disagreements remain. Trigger…
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (docs/GLOSSARY.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language…
Find deepening opportunities in a codebase, informed by the domain language in docs/GLOSSARY.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a…
Session bookmark. Triggers when user says 'wrap up', 'done for today', /wrap-session, or when closing a work session on a CONTEXT.md-bearing project. Rewrites .attacca/focus.md, appends new decisions to CONTEXT.md, and surfaces repeated corrections as…
Initialize a new project from scratch. Read spec from CONTEXT.md or ask interactively, scaffold directories, set up .gitignore and basic configs, create CONTEXT.md, commit. Use when starting a new project.
Disambiguate vague build requests through structured questioning. Triggers when user says 'build me X' implying 2+ unresolved dimensions (auth/payments/data/integrations), has new-project or major-feature scope with unresolved decisions, or user says…
Retrofit an existing project with Attacca. Audit project structure, generate CONTEXT.md from what you find, merge settings safely, suggest plugins. Never touches source code or existing deployments.
Falsification-first validation for a product, startup, feature, or side-project idea. Decomposes the idea into load-bearing assumptions, pre-registers kill criteria before looking at evidence, runs cost-ordered disqualifiers, gathers cited evidence into a…
Token compression skill. Use when: context window is filling up, on long-running multi-session tasks, when user needs faster/cheaper agent responses, or when working in bandwidth-constrained environments. Reduces output tokens 65–75% by switching to…
Runbooks and decision frameworks for production incidents and emergencies. Use when: service is down, critical feature broken, data loss risk, security breach detected. Covers triage, classification, symptom-to-fix matching, and incident logging.
Pre-push quality gate checklist. Use when: before any git push, before opening a PR, after implementing a full feature. Runs lint, type-check, tests, and a security scan as a single sequential gate. Fails fast — does not proceed past a failing stage.
TDD workflow skill enforcing RED → GREEN → REFACTOR. Use when: implementing any feature test-first, writing unit or integration tests, building with a test-heavy stack (Jest, Vitest, pytest, RSpec, etc.). Prevents writing implementation before a failing test…
BDR commit discipline: Business/Decision/Rationale format making every commit auditable and falsifiable. Triggers when user says 'bdr commit', asks to commit a feature, or a non-trivial implementation is complete. Never add Co-Authored-By or AI attribution.
On-demand code review checklist. Use when: reviewing code changes, PR review, self-review before committing, checking code quality after implementation. Covers readability, correctness, performance, security, and maintainability.
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or…
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria. Inspired by Andrej Karpathy's…
Build and maintain a persistent, compounding LLM-maintained knowledge base (wiki). Use when: setting up a second brain for a project or personal knowledge base, processing PDFs/articles/notes into structured wiki pages, querying accumulated knowledge with…
Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user…
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
Turn the current conversation context into a PRD and publish it as a GitHub Issue. Use when user wants to create a PRD from the current context.
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
Ship a working MVP as fast as possible. Ruthless scope, aggressive defaults, skip non-essential gates. For speed-first projects where 'done' beats 'perfect'.
Welcome guide for new users. Assesses your setup, explains what Attacca does, points to first action. Run this first if you're new.
Generate a Software Bill of Materials (SBOM) and scan for CVEs. Use before production pushes, when dependency files change, or on security request. Artifacts written to .attacca/sbom/.
On-demand security audit checklist based on OWASP Top 10. Use before any git push. Reports written to .attacca/audits/latest.md with verdict that unlocks the push gate.
4-gate supply chain security checklist. Prevents malicious packages, typosquatting, and abandoned projects. Use before adding any dependency to production. Can run standalone.