Agent skill

Skill Library Mission

by athola in athola/claude-night-market

Build a project skill library in .claude/skills/ via discovery, parallel authoring, and review.

MITAuto-check passedDevelopment

Install Skill Library Mission

skills CLI
$ npx skills add athola/claude-night-market --skill skill-library-mission -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install athola/claude-night-market skill-library-mission --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/attune/skills/skill-library-mission .claude/skills/skill-library-mission && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
skill-library-mission
GitHub stars
341
Token cost
~1.6k tokens
SKILL.md length
686 words
Files
5 (incl. references)
Skills in repo
152
Repo updated
First seen
Licence
MIT

At a glance

Build a project skill library in .claude/skills/ via discovery, parallel authoring, and review.

  • Works in 3 steps: Discover → Author → Review
  • Packaging tribal knowledge
  • SKILL.md covers Overview, When To Use, When NOT To Use and Mission Shape, plus 6 more sections
  • Calls rg

What it does

Skill Library Mission is an agent skill from athola/claude-night-market. Build a project skill library in .claude/skills/ via discovery, parallel authoring, and review. Use when packaging tribal knowledge. Do not use for one skill.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `modules/authoring-rules.md`, `modules/review-protocol.md` and `modules/taxonomy.md`).

It sits in Development. The repository describes itself as: 23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context… The licence is MIT.

When your agent uses it

  • Packaging tribal knowledge

Example prompts

  • “/skill-library-mission”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Discover
  2. Author
  3. Review

What it can do on your machine

Read from SKILL.md and the folder at commit 9f3eb00. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • rg

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Skill Library Mission loads about 1.6k tokens when it runs, and up to ~3.5k if it reads all its reference files. Until then it costs about 45 tokens; SKILL.md has 686 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from athola/claude-night-market at commit 9f3eb00, republished under its MIT licence (© athola). 686 words, ~1,553 tokens.

Download SKILL.mdSave it as .claude/skills/skill-library-mission/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
skill-library-mission
description
Build a project skill library in .claude/skills/ via discovery, parallel authoring, and review. Use when packaging tribal knowledge. Do not use for one skill.
alwaysApply
false
category
workflow-orchestration
tags
skill-library, knowledge-transfer, succession, mission, multi-agent
dependencies
attune:mission-orchestrator, abstract:skill-authoring, imbue:proof-of-work
provides.workflow
skill-library-authoring, knowledge-transfer, succession-planning
usage_patterns
repo-succession, onboarding-library, institutional-memory
complexity
advanced
model_hint
deep
estimated_tokens
700
progressive_loading
true

Skill Library Mission

Overview

A retiring distinguished fellow's final task: package everything the project knows into a skill library under .claude/skills/, so that cheaper sessions and newer engineers can carry the project forward at the same standard. This skill turns that one-off exercise into a repeatable mission with three gated phases: discover, author, review.

The mission produced its first library in this repository on 2026-07-02 (15 skills, mission skill-library-2026-07-02). The generalized dispatch prompt distilled from that run is preserved verbatim in references/mission-prompt.md.

When To Use

  • A repository has deep tribal knowledge and no .claude/skills/ library, and future sessions (human or model) must operate without the current expert.
  • An existing project library has drifted and needs a full re-discovery and re-review pass.
  • Onboarding cost is high: the same questions get re-answered and the same dead ends get re-fought across sessions.

When NOT To Use

SituationUse instead
Authoring or improving one skillSkill(abstract:skill-authoring)
Skills shipped inside a pluginSkill(plugin-dev:skill-development)
Auditing existing skills onlySkill(abstract:skills-eval)
Full project lifecycle (code, not knowledge)Skill(attune:mission-orchestrator)

Mission Shape

Run as an attune mission with custom phases so the run survives interruption and records user directives:

json
{
  "mission_id": "skill-library-YYYY-MM-DD",
  "type": "custom",
  "phases": ["discover", "author", "review", "report"],
  "artifacts": { "library_root": ".claude/skills/" }
}

Save this to .attune/mission-state.json, advance current_phase at each gate, and record every user decision and override in decisions / directive_overrides. A later session must be able to resume from the state file alone.

Phase 1: Discover

No authoring happens in this phase. Investigate like an incoming principal engineer:

  • README, manifest, contributor docs
  • Build system and how tests actually run (not how docs claim)
  • CI config and quality gates
  • Git history: what changed, what got reverted, what stalled
  • TODO/FIXME hotspots and issue-shaped artifacts
  • Generated-data, deploy, and artifact conventions
  • Any project memory available (discussions, ADRs, journals)

Then ask the user at most five questions, only for what the repo cannot tell you. The canonical five: the hardest live problem, unwritten discipline rules, the audience and what it lacks, the most expensive past failures, and what "beyond state of the art" means here. Fold the answers into every later phase.

Phase 2: Author

workflows/skill-library.js runs authoring and review as one pipeline, so each skill's review starts when that skill is written rather than when the slowest one is. It runs only when asked for, and it returns review findings instead of applying them, because fixing edits files that already exist. Without it, dispatch by hand:

Dispatch one authoring agent per skill, in parallel, following the taxonomy in modules/taxonomy.md (adapt it: merge thin categories, split deep ones, add domain categories). Aim for 10 to 16 skills. Every agent prompt embeds the rules in modules/authoring-rules.md; the non-negotiables are ground-truth-only claims, a "Provenance and maintenance" section per skill, and a write fence limiting agents to .claude/skills/.

Show full SKILL.md (238 more words)Show less

Phase 3: Review

After all skills exist, run the three-reviewer-plus-fixer protocol in modules/review-protocol.md: factual, doctrine, and usability lenses in parallel, then one fixer applying blocking and important findings. Finish with the report: skill inventory with one-line descriptions, what was spot-checked, and what remains uncertain.

Constraints

  • Run discovery even on a small repository. The five questions come from it, and there is no other source for them.
  • Verify against ground truth even in a codebase you know. A wrong runbook is worse than none.
  • Review the library even when it looks complete. Authoring agents cannot see each other's contradictions.
  • Date-stamp every claim and give it a re-verification command. A claim that is probably still true is a claim nobody checked.

Exit Criteria

  • .attune/mission-state.json exists with the custom phase list and reaches report with all prior phases completed.
  • .claude/skills/ contains 10 to 16 skill directories, each with a SKILL.md whose frontmatter has name and a trigger-rich description.
  • Every skill ends with a "Provenance and maintenance" section containing one-line re-verification commands.
  • All three review lenses ran and every blocking or important finding is either applied or skipped with a recorded reason.
  • The final report lists the inventory, spot-check evidence, and remaining uncertainties.

Provenance and Maintenance

  • Origin: mission skill-library-2026-07-02 in claude-night-market; generalized prompt captured 2026-07-03.
  • Verify the reference prompt still matches this skill's phases: rg -c "Phase" plugins/attune/skills/skill-library-mission/references/mission-prompt.md
  • Verify the first library still exists where this skill claims: ls .claude/skills/ | head -5

© athola, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in plugins/attune/skills/skill-library-mission of athola/claude-night-market.

  • SKILL.md
  • modules/authoring-rules.md
  • modules/review-protocol.md
  • modules/taxonomy.md
  • references/mission-prompt.md

Open the folder on GitHubat commit 9f3eb00

Compare with similar skills

Skill Library Mission next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Skill Library Mission compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Library Mission this skillathola/claude-night-market341—~1.6kAutomated safety check: PassMIT
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k4 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 4 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from athola/claude-night-market

All 152 skills in this repo
  • Night Market Diagnostics Toolkit

    athola/claude-night-market

    Run and interpret repo diagnostic scripts (ratchets, validators, token stats).

    341 GitHub stars~3.4k tokensUpdated yesterday
    Auto-check passed
  • Skills Eval

    athola/claude-night-market

    Evaluate Claude skill quality through auditing. An agent skill from athola/claude-night-market.

    341 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Agent Teams

    athola/claude-night-market

    Coordinates Claude agent teams via filesystem protocol. An agent skill from athola/claude-night-market.

    341 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed
  • Delegation Core

    athola/claude-night-market

    Delegates execution to eight CLIs (Gemini, Qwen, MiniMax, GLM, Muse, Codex, OpenCode, Glimmer).

    341 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed
  • Elegant Code

    athola/claude-night-market

    Guide minimal code via a decision ladder with full safety, edge, and negative-case coverage.

    341 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • Mission Orchestrator

    athola/claude-night-market

    Orchestrates full project lifecycle by auto-detecting state and routing to the correct phase.

    341 GitHub stars~3.4k tokensUpdated yesterday
    Auto-check: warnings

Categories

Questions about Skill Library Mission

What does Skill Library Mission do?

Build a project skill library in .claude/skills/ via discovery, parallel authoring, and review. Skill Library Mission is an agent skill from athola/claude-night-market.claude/skills/ via discovery, parallel authoring, and review.

When should I use Skill Library Mission?

Skill Library Mission fits situations like: packaging tribal knowledge.

How do I install Skill Library Mission in Claude Code?

Run `npx skills add athola/claude-night-market --skill skill-library-mission -a claude-code`. Or copy the skill folder (plugins/attune/skills/skill-library-mission in athola/claude-night-market) into .claude/skills/skill-library-mission in your project. Claude Code loads it when a task matches its description.

How do I install Skill Library Mission in Codex?

Run `npx skills add athola/claude-night-market --skill skill-library-mission -a codex`. Or copy the skill folder (plugins/attune/skills/skill-library-mission in athola/claude-night-market) into .agents/skills/skill-library-mission in your project. Codex loads it when a task matches its description.

Can I use Skill Library Mission in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add athola/claude-night-market --skill skill-library-mission -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-library-mission, .gemini/skills/skill-library-mission, .github/skills/skill-library-mission and .opencode/skills/skill-library-mission in your project.

What does Skill Library Mission need to run?

Going by SKILL.md and its folder, Skill Library Mission needs the command-line tools its instructions call (rg).

Does Skill Library Mission access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Skill Library Mission safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Skill Library Mission use?

Skill Library Mission is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skill Library Mission use?

About 1.6k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2k tokens, read only when the agent opens those files.

What are the alternatives to Skill Library Mission?

Skills that share tags, products or a category with Skill Library Mission: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Library Mission?

athola (a GitHub user) maintains it in athola/claude-night-market, which has 341 GitHub stars. The repository holds 152 skills in this directory. The repository was last updated on October 9, 2026.

Source: athola/claude-night-market on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.