failure-pattern-library
Consult and extend a process failure-pattern library: the admission criteria, the evidence each entry must preserve, and the fields that make a criterion…
Skill by emliunix
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/emliunix-failure-pattern-library
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/failure-pattern-library
What's inside
- Skill name
failure-pattern-library- Description
- Consult and extend a process failure-pattern library: the admission criteria, the evidence each entry must preserve, and the fields that make a criterion evaluable rather than aspirational. Use when a process or communication failure is found and must be captured, when deciding whether an observation qualifies as a pattern, or when checking whether a recorded pattern has recurred.
- License
- GPL-3.0
- Instructions
- 47 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (7)
- CHANGELOG.md
- README.md
- SKILL.md
- criteria.md · references/
- entry-template.md · references/
- l0.py · tests/
- seeded-defects.md · tests/
SKILL.md (first lines)
# Failure-pattern library A library of process and communication failures, kept as **raw material for continuous improvement** of docs, prompts, skills, and project setup. Use it two ways: **capture** a failure you just found, and **consult** what is already recorded before adding a near-duplicate. ## The one path rule, and it governs this whole skill > **This guide names NO specific project, repository, or PC path — only the general library root > `~/Documents/process-failure-patterns/<project>/`.** **Why it is first, and why it is a rule rather than a style note:** a skill is loaded into every session on every host that links it, and a skill in a shared repository is public. **A literal path makes the guide true on exactly one machine and stale on all others.** A dated capture about *this* project may name it; **guidance about how to keep the library may not.** ⚠ **Apply the rule to the rule.** If this file, or a criteria list, names a path that is not the general root, that is the defect the rule exists to prevent — including when the path looks familiar. ## Capture 1. **Preserve the smallest reproducible source.** A quoted fragment, a command and its output, a message id — not a paraphrase and not the whole transcript. 2. **Write the entry** against `references/entry-template.md`. **Fields are not decoration: a criterion you cannot evaluate is not a criterion.** If a field's data does not exist, record `not captured` rather than guessing it. 3. **Correct the process.** *A capture without the correction is a museum.* Name what changed — a doc, a prompt, a skill, a check — or record why no correction is warranted. 4. **Check for a near-duplicate before adding.** Search by **mechanism**, not by the rule's name; a rule is often carried as a citation rather than as a statement. If a sibling entry already states it, **link it rather than re-entering it** — a library that grows by re-entry stops being an index. ## Consult - **Before asserting a rule**, check whether it is already recorded — and whether it was **retracted**. A retraction that reached only the artifact that prompted it leaves the false rule live in every sibling. - **When counting the library**, state the predicate with the count. `grep -c` over an index counts prose *about* the entries as well as the entries. ## Criteria See `references/criteria.md` for the admission and classification criteria, and `references/entry-template.md` for the fields each entry carries. **Read both together**: a criterion in the list whose field is absent from the template is unenforceable, and the template is where a new criterion starts being real.
From emliunix/home.conf, GPL-3.0.
More from emliunix/home.conf
- 0.570score
efficient-tool-use
emliunix
Apply evidence-based rules when composing tool calls, parsing their output, interpreting non-zero exits, or turning repeated operations into durable routines.
SkillAFreshness: AClaude Code +9 - 0.570score
audit-agent-tooling
emliunix
Audit how agents actually use tools and skills from session transcripts, separate crash rate from correctness, identify repeated operations that should become…
SkillAFreshness: AClaude Code +9 - 0.566score
code-analysis-cookbook
emliunix
Recipes for code ANALYSIS and code EDITING with compiler, language-server, structural-AST and reference tools: typecheck a package, rename a symbol…
SkillAFreshness: AClaude Code +9 - 0.565score
adversarial-evaluate
emliunix
Multi-seat adversarial evaluation of work: a fixed review set derived from the commit range, independent seats chosen for model diversity rather than assigned…
SkillAFreshness: AClaude Code +9 - 0.565score
code-quality
emliunix
Use for current-model / era-reachability gates, suite discipline, or when a local identity is packed into a string (startsWith, slice, colon-join…
SkillAFreshness: AClaude Code +9 - 0.565score
compatibility-design
emliunix
Use when a design or implementation proposes compatibility, fallback, dual-world, migration, or history-gated shape selection, including phrasings like…
SkillAFreshness: AClaude Code +9 - 0.565score
experiment-round
emliunix
First-principles experiment rounds and the programmes that hold them: one hypothesis, one axis, two or three genuine candidates, expectations pre-registered…
SkillAFreshness: AClaude Code +9 - 0.565score
blind-trial
emliunix
Blinded trials as the measurement of a record or a surface: reader batches over the spine (trajectory, per-reader metrics) and author rounds (blind and…
SkillAFreshness: AClaude Code +9 - 0.565score
eval-prompt
emliunix
Evaluate an instruction artifact by blinded trials: control, entry-only and full arms, trajectory plus post-trial feedback, rubrics by case (trigger…
SkillAFreshness: AClaude Code +9 - 0.529score
esp-dev
emliunix
ESP32 / ESP-IDF firmware development and bring-up practice distilled from our vibe-s3, vibe-s31 and nfcplay projects: board wiring and serial-port mapping…
SkillBFreshness: BClaude Code +9 - 0.524score
agent-detox
emliunix
Use only with gpt-5.6-sol when the user mentions agent-detox, 解毒剂, or its over-defensive behavior.
SkillBFreshness: BClaude Code +9 - 0.474score
coop-design
emliunix
Collaborative design workflow for architecture and system design.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 1
- Open issues
- 3
- Last commit (this folder)
- Oct 17, 2026 (12 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- GPL-3.0
- Repository
- github.com/emliunix/home.conf
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from emliunix
- 0.570score
efficient-tool-use
emliunix
Apply evidence-based rules when composing tool calls, parsing their output, interpreting non-zero exits, or turning repeated operations into durable routines.
SkillAFreshness: AClaude Code +9 - 0.570score
audit-agent-tooling
emliunix
Audit how agents actually use tools and skills from session transcripts, separate crash rate from correctness, identify repeated operations that should become…
SkillAFreshness: AClaude Code +9 - 0.566score
code-analysis-cookbook
emliunix
Recipes for code ANALYSIS and code EDITING with compiler, language-server, structural-AST and reference tools: typecheck a package, rename a symbol…
SkillAFreshness: AClaude Code +9 - 0.565score
code-quality
emliunix
Use for current-model / era-reachability gates, suite discipline, or when a local identity is packed into a string (startsWith, slice, colon-join…
SkillAFreshness: AClaude Code +9 - 0.565score
adversarial-evaluate
emliunix
Multi-seat adversarial evaluation of work: a fixed review set derived from the commit range, independent seats chosen for model diversity rather than assigned…
SkillAFreshness: AClaude Code +9 - 0.565score
compatibility-design
emliunix
Use when a design or implementation proposes compatibility, fallback, dual-world, migration, or history-gated shape selection, including phrasings like…
SkillAFreshness: AClaude Code +9
Cite this page
failure-pattern-library skill. Agent Mart. https://agentmart.dev/skills/emliunix-failure-pattern-library (last updated 2026-10-24)