audit

Use when the user asks to audit a memex (long-term knowledge bank for AI agents) for orphans, dead SALP REFs, missing sections, contradictions, or index drift. Runs a deterministic structural check, layers LLM-judgement findings, optionally auto-fixes trivial issues with `--fix`. Do NOT trigger on general code linting.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

68%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable skill body with clear sequencing and good organization. The main weaknesses are a missing post-fix verification loop for batch auto-fixes and a referenced bundled script that is absent from the bundle.

Suggestions

Add a verification step after the --fix pass: re-run `deno run --allow-read scripts/audit.ts <memex-root>/pages/` and confirm previously reported DEAD_LINK/MISSING_SECTION/INDEX_* issues are resolved before writing the report.

Either include the referenced `scripts/audit.ts` in the ./scripts/ bundle or note explicitly that it is installed separately, so the headline command is verifiable.

De-duplicate the 'long-term knowledge bank for AI agents' gloss (already in the frontmatter) from the body's opening line to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly lean and well-organized with tables and templates rather than prose, assuming Claude's competence; minor redundancy such as repeating 'long-term knowledge bank for AI agents' and some template verbosity could be trimmed.	4 / 5
Actionability	Provides concrete executable commands (`deno run --allow-read scripts/audit.ts`, `grep -rln "[!WARNING]"`) and exact issue/output formats plus stub and report templates, but the headline command depends on a bundled script that is not present in the bundle, leaving a small gap.	4 / 5
Workflow Clarity	A clear six-step sequence (run check, layer LLM-judgement, auto-fix, write report, append log, report) is present, but this batch/auto-fixing skill lacks a post-fix re-validation loop (e.g. re-running the audit script to confirm fixes resolved the issues), which caps it at 3 per the batch-operation feedback-loop rule.	3 / 5
Progressive Disclosure	Good single-file structure with clear section headers and a one-level-deep, well-signaled reference to `scripts/audit.ts`; the gap is that the referenced bundle file does not actually exist in ./scripts/, so it is just short of a clean 5.	4 / 5
	Total	15 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A tight, well-scoped description that clearly states both capability and trigger conditions while explicitly disambiguating from code linting. Only minor weakness is a lack of synonym variation in trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — auditing for orphans, dead SALP REFs, missing sections, contradictions, index drift, plus running a deterministic check, layering LLM-judgement, and auto-fixing with --fix — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('Runs a deterministic structural check, layers LLM-judgement findings, optionally auto-fixes') and when ('Use when the user asks to audit a memex...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural terms ('audit a memex', 'orphans', 'dead SALP REFs', 'contradictions', 'index drift') that users would say, but lacks common synonyms like 'check'/'health check' so it is just short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (memex auditing) with distinct triggers and an explicit exclusion ('Do NOT trigger on general code linting'), minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: korchasa/flowai-plugins
Path: plugins/flowai-memex/skills/audit/SKILL.md
Commit: b4ba256

Reviewed: ~21 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.