Menu
SkillsMP a collecté 65 skills depuis merceralex397-collab/skilllibrary. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 40 skills collectés sur 65.
Design and harden agent, command, workflow, and tool prompts for reliable execution across different AI models. Use when creating or revising repo-local agents to apply model-specific prompting techniques, tighten scope, and prevent common agent failure modes…
Langue du texte source : anglais
Find external skills from public registries, GitHub repos, and official skill collections, then evaluate them for quality, licensing, and fitness for adoption. Use when looking for existing skills before building from scratch, evaluating external skill…
Langue du texte source : anglais
Create concise project handoff artifacts, especially a top-level START-HERE document and short resume context for the next session or machine. Use when scaffolding finishes, a milestone closes, or long-running autonomous work needs a compact restart surface.…
Langue du texte source : anglais
Generate structured migration plans with inventory, risk-ranked sequence, rollback procedures, and acceptance criteria for major upgrades or framework migrations. Use when upgrading major dependencies (React 17→18, Python 3.9→3.12), migrating frameworks…
Langue du texte source : anglais
Design and generate a project-specific agent team with specialized agents, tools, plugins, commands, and skills tailored to the project type and stack. Use after the base scaffold exists to customize generic agent templates into project-aware specialists. Do…
Langue du texte source : anglais
Generate client-specific overlay files (metadata, permissions, manifests) from a canonical SKILL.md source for different AI agent clients. Use when publishing a skill to multiple ecosystems (Copilot, OpenCode, Codex, Gemini CLI), converting between overlay…
Langue du texte source : anglais
Review a pull request, validate review comments against the actual implementation, and generate follow-up tickets only for findings that survive evidence-based triage. Use after a PR review cycle when comments need to be triaged into actionable work items. Do…
Langue du texte source : anglais
Create project-local skills populated with actual project data, stack-specific conventions, and domain-specific procedures. Use after scaffolding to replace generic skill placeholders with real project-aware guidance that helps agents work effectively in this…
Langue du texte source : anglais
Audit a skill or artifact's origin chain: where it came from, who authored it, what license applies, what modifications were made, and what trust level to assign. Use when evaluating external skills for adoption, auditing existing skills for license…
Langue du texte source : anglais
Audit existing repositories for agent-workflow drift and repair opportunities. Use when a repo has custom agents, commands, process docs, or ticket systems and you need to diagnose contradictory status semantics, raw-file stage control, missing workflow-state…
Langue du texte source : anglais
Maintain START-HERE, context snapshots, and closeout artifacts for this repo. Use when a ticket changes state, a session is ending, or autonomous work needs a concise human and agent resume surface.
Langue du texte source : anglais
Load the local source-of-truth docs for this repo. Use when an OpenCode agent needs the project mission, canonical brief, workflow, ticket state, or current operating status before planning, implementing, reviewing, or handing off work.
Langue du texte source : anglais
Navigate the canonical docs, ticket files, and OpenCode operating surfaces for this repo. Use when an agent needs to find where process, state, or handoff information lives without scanning the entire repository.
Langue du texte source : anglais
Hold the project-local standards for languages, frameworks, validation, and runtime assumptions. Use when planning or implementing work that should follow repo-specific engineering conventions.
Langue du texte source : anglais
Follow the required ticket lifecycle for this repo. Use when an agent is advancing a ticket through planning, review, implementation, QA, and closeout and needs the repo-specific stage rules.
Langue du texte source : anglais
Inspect bootstrap provenance, invocation tracking, and workflow state to explain which repo-local agents, tools, plugins, and skills are actually being exercised.
Langue du texte source : anglais
Generate the base repository file structure including README, AGENTS.md, docs layout, ticket templates, and the agent configuration scaffold. Use when creating a greenfield repo foundation or resetting a weakly structured project. This generates a generic…
Langue du texte source : anglais
Orchestrate the full spec-to-repo kickoff flow for greenfield or early-stage projects. Use when asked to scaffold, generate, or bootstrap a new project repository from specs, plans, or requirements. This is the single entrypoint — it sequences all sibling…
Langue du texte source : anglais
Safely deprecate, retire, or merge obsolete skills while preserving backward references and library clarity. Use when a user says 'deprecate this skill', 'retire this', or 'this is replaced by X', when a catalog audit identifies a skill for retirement, or…
Langue du texte source : anglais
Rewrite a skill's description field to fix routing problems — undertriggering, overtriggering, or passive language that fails to match user intent. Use when a skill isn't being found by agents, evaluation shows low trigger recall, or batch-auditing…
Langue du texte source : anglais
Run trigger tests, behavior tests, and baseline comparisons for a skill's eval suite, then produce a structured quality verdict. Use when a skill has been modified and needs regression testing, when CI/pre-release validation requires documented eval results,…
Langue du texte source : anglais
Build distributable bundles, manifests, and checksums for publishing or sharing one or more skills. Use when packaging skills for release, building a distribution bundle, creating CI/CD skill artifacts, or releasing a new library version. Do not use for…
Langue du texte source : anglais
Maintain the skill library catalog: add entries, update metadata, manage tags, track maturity/status, enforce naming conventions, and generate the library index. Use when adding a new skill to the registry, updating skill metadata after changes, auditing…
Langue du texte source : anglais
Normalize one or more source specs, notes, pasted chats, and Markdown planning documents into a single canonical brief, decision packet, and constraints summary. Use when given messy or multi-file project requirements that need to become a clean source of…
Langue du texte source : anglais
Detect a project's language, framework, runtime, testing setup, and deployment target from repository contents and produce a structured STACK-PROFILE.md. Use when scaffolding a new project and need to determine stack from code evidence, onboarding to an…
Langue du texte source : anglais
Create a repo-local ticket system with an index, machine-readable manifest, board, and individual ticket files. Use when a repo needs task decomposition that autonomous agents can follow without re-planning the whole project each session. Do not use for…
Langue du texte source : anglais
Adapt a general-purpose skill to a specific repository, team, stack, or project context without losing the base pattern. Use this when porting a skill between stacks (e.g. React to Vue, npm to pnpm), customizing a library skill for project conventions, or…
Langue du texte source : anglais
Audit a SKILL.md for structural anti-patterns that reduce routing accuracy, output quality, or maintainability. Use this for pre-promotion reviews, post-failure diagnostics, or quick structural audits when a skill feels "off" but the problem is unclear. Do…
Langue du texte source : anglais
Write a new SKILL.md file with correct YAML frontmatter, routing description, and structured body sections when a user needs to create a skill from scratch. Use this for requests like "create a skill for X", "write a skill that handles Y", "I need a new skill…
Langue du texte source : anglais
Compare skill variants or before-and-after versions using pass rate, token usage, latency, and qualitative win rate. Use this when choosing between multiple skill variants, measuring whether a refinement helped, or justifying skill maintenance investment. Do…
Langue du texte source : anglais
Audit and organize a skill library as a whole — detect duplicates, enforce category consistency, mark deprecation candidates, and ensure discoverability. Use this when the library has grown large enough that overlaps and inconsistencies emerge, before major…
Langue du texte source : anglais
Create a complete new skill end-to-end — from understanding requirements through initialization, implementation, validation, and forward-testing. Use this when a user wants to build a new skill from scratch using the Codex skill framework, including running…
Langue du texte source : anglais
Evaluate whether a skill routes correctly and produces better output than a baseline — measuring precision, recall, output quality, and win rate against no-skill runs. Use this when validating a new skill before promotion, verifying a refinement worked, or…
Langue du texte source : anglais
REDIRECTED — This skill has been merged into skill-installer, which handles all skill installation workflows. Use skill-installer instead.
Langue du texte source : anglais
Install skills into an agent client environment from a curated registry, GitHub repository, local folder, or packaged bundle. Use this when the user says "install this skill", "add skill from GitHub", "list available skills", "set up skill X", or asks about…
Langue du texte source : anglais
Manage skills through lifecycle states — draft, beta, stable, deprecated, archived — applying promotion criteria, deprecation rules, and transition tracking. Use this when auditing skill maturity across a library, promoting a tested skill to stable, retiring…
Langue du texte source : anglais
Package a skill folder into a distributable bundle (tarball or zip) with manifest, integrity checksums, and optional client-specific overlays. Use this when preparing a skill for sharing outside the source repository, publishing to a registry, or creating a…
Langue du texte source : anglais
Document the origin, authorship, evidence basis, and encoded assumptions of a skill to establish trust and traceability. Use this when publishing a skill to a shared registry, importing from an external source, auditing library trustworthiness, or when a…
Langue du texte source : anglais
Extract large reference material (schemas, examples, lookup tables, API docs) from a bloated SKILL.md into a references/ directory for progressive disclosure. Use this when a SKILL.md exceeds 500 lines or 10KB, contains large code examples or schemas not…
Langue du texte source : anglais
Make targeted, surgical fixes to an existing skill based on observed failure modes — tightening vague language, fixing routing misses, removing bloat, or covering missed edge cases. Use this when a skill produces inconsistent output, triggers incorrectly, or…
Langue du texte source : anglais