code-analysis-cookbook
Recipes for code ANALYSIS and code EDITING with compiler, language-server, structural-AST and reference tools: typecheck a package, rename a symbol…
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-code-analysis-cookbook
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
Use cases: backend, security, writing, research
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
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/code-analysis-cookbook
What's inside
- Skill name
code-analysis-cookbook- Description
- Recipes for code ANALYSIS and code EDITING with compiler, language-server, structural-AST and reference tools: typecheck a package, rename a symbol everywhere, find every caller, resolve a citation to its definition, count a population with its predicate. Use when a task is to learn a fact about code or to change code by its structure, especially before reaching for grep/sed. Topics live under this one handle; read the topic that matches the task. Do not use for general tool use or transcript auditing (see efficient-tool-use and audit-agent-tooling).
- License
- GPL-3.0
- Instructions
- 80 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- files: referenced but missing: scripts/local/typecheck-all.sh
Files (13)
- SKILL.md
- 2026-10-03-evaluation.md · evidence/
- citation-and-population.md · references/
- diagnostic-rules.md · references/
- native-prerequisites.md · references/
- proposals.md · references/
- service-state.md · references/
- structural-search.md · references/
- symbol-edit.md · references/
- symbol-outline.md · references/
- typecheck.md · references/
- patch-pi-lens-lsp-limit.mjs · scripts/
- typecheck-all.sh · scripts/
SKILL.md (first lines)
# Code-analysis cookbook One trigger, task-grouped recipes. Read only the chapter that matches the task in front of you; the chapter files are the durable recipes, not this routing surface. **The default is structural, not textual.** A text pattern stands in for the structure it means: `sed s/old/new/` matches a *string*, so it rewrites comments and test names that merely contain it, and a structural pattern that cannot see a construct reports "no match" exactly like a genuine absence. Reach for the structural tool first and keep text search as a documented fallback — with the knowledge of which one you are holding. **Every recipe states its failure mode**, and that column is the reason this cookbook exists. Checked-and-clean must be distinguishable from could-not-read: a tool that refuses a target, exceeds a size limit, or holds a stale index has **not** answered, and its silence must never be read as a pass. ## Chapters - **`code-analysis-cookbook/typecheck`** — [typecheck.md](references/typecheck.md): typecheck a package and its tests; the gap where `pnpm check` is green while a package does not compile. - **`code-analysis-cookbook/symbol-edit`** — [symbol-edit.md](references/symbol-edit.md): rename a symbol, find every caller, and read the enclosing symbol before editing a line. - **`code-analysis-cookbook/service-state`** — [service-state.md](references/service-state.md): judge a service by what it serves, not by what it reports; `active (exited)` is not "started". - **`code-analysis-cookbook/native-prerequisites`** — [native-prerequisites.md](references/native-prerequisites.md): six ways a library reports "not found", with the different fix each needs. - **`code-analysis-cookbook/diagnostic-rules`** — [diagnostic-rules.md](references/diagnostic-rules.md): judge a lint rule by what it read; a rule can fire correctly and be wrong, and its own test corpus can be the reason. - **`code-analysis-cookbook/symbol-outline`** — [symbol-outline.md](references/symbol-outline.md): learn a large file's shape from an outline instead of reading its bytes. - **`code-analysis-cookbook/structural-search`** — [structural-search.md](references/structural-search.md): AST search and preview-then-apply replacement; what it can and cannot see. - **`code-analysis-cookbook/citation-and-population`** — [citation-and-population.md](references/citation-and-population.md): resolve a locator to the thing it names, and count a population with its predicate printed. ## Proposals (not recipes) Tools nobody on this host has run end to end are listed in [proposals.md](references/proposals.md) as candidates with their prerequisites, never as recipes. Move one here only when a seat has executed it and recorded the failure mode. ## Runnable `scripts/typecheck-all.sh` — the non-gate form of the typecheck chapter: runs every workspace package's typecheck, attributes each error to the FILE that carries it, and refuses to report a pass when it found no `tsconfig.json` at all. Copy it into a repo as `scripts/local/typecheck-all.sh` and run with `sh`. **It changes no repository gate** — wiring a `typecheck` entry into a repo's aggregate check is a separate decision. `scripts/patch-pi-lens-lsp-limit.mjs` — raises pi-lens 4.3.0's hardcoded LSP-sync line bound from 5000 to 10000 in the installed package, with `--revert` to restore stock. It is a host patch, not a supported pi-lens setting; re-run it after an install and start a fresh Pi session. ## Evidence Source cases: agent-substrate, 2026-10-03 — the #99 port race, #94's landed type errors behind a green gate, and the citation/population findings in the #88/#95/#98 chain. Every invocation in the chapters was run on this host; where a claim is quoted from another seat it says so and names the message. Add a recipe only when it changed a decision and its invocation is reproducible on this host (or is marked with its missing prerequisite). Replace a superseded recipe in place rather than keeping contradictory versions.
From emliunix/home.conf, GPL-3.0.
More from emliunix/home.conf
- 0.570score
failure-pattern-library
emliunix
Consult and extend a process failure-pattern library: the admission criteria, the evidence each entry must preserve, and the fields that make a criterion…
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 - 0.570score
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 - 0.565score
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 - 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
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
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 - 0.565score
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 - 0.529score
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 14, 2026 (14 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
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 - 0.570score
failure-pattern-library
emliunix
Consult and extend a process failure-pattern library: the admission criteria, the evidence each entry must preserve, and the fields that make a criterion…
SkillAFreshness: AClaude Code +9 - 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 - 0.565score
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
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
Cite this page
code-analysis-cookbook skill. Agent Mart. https://agentmart.dev/skills/emliunix-code-analysis-cookbook (last updated 2026-10-24)