citation-fixer

Audit and fix citation formatting across brain pages. Ensures every fact has an inline [Source: ...] citation matching the standard format. Extended in v0.25.1: scans for broken tweet/post references that lack actual URLs and resolves them via the host's X / Twitter API integration.

Quality

61%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/citation-fixer/SKILL.md

Quality

Content

57%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.

The body is actionable and well-structured with concrete scripts and query patterns, but as a mutating batch skill it lacks explicit post-patch validation, capping workflow clarity, and it carries mild verbosity plus an inlined long pipeline that limits progressive disclosure.

Suggestions

Add an explicit validate-after-patch checkpoint (e.g. re-scan the patched page to confirm the new x.com citation resolves and the surrounding context still parses) so workflow clarity can score above 3 for this batch/mutating skill.

Move the detailed tweet-resolution pipeline (Steps 1-5) into a separate reference file and keep SKILL.md as an overview with a one-level-deep pointer, improving progressive disclosure.

De-duplicate the duplicate 'Output Format' section and consolidate the repeated v0.25.1 annotations into a single version note to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes competence, but repeats the v0.25.1 annotation across sections, restates 'Output format' twice (once as a real section and once as a conformance-test stub), and includes light padding, fitting 'mostly efficient but could be tightened' rather than the lean level 4.	3 / 5
Actionability	It gives mostly executable guidance — concrete grep/find bash for candidate pages, exact X API query patterns, before/after citation patches, and a JSON state schema — with only minor gaps, matching the 'mostly executable' anchor.	4 / 5
Workflow Clarity	The tweet-resolution pipeline is clearly sequenced with numbered steps, but this is a mutating/batch skill and validation after patching the brain page is only implicit (the cap for batch/destructive workflows without explicit validation applies), so it cannot exceed 3 despite the good structure.	3 / 5
Progressive Disclosure	Sections provide reasonable structure and there are one-level-deep external references (conventions/quality.md, _output-rules.md), but no bundle files exist and the long tweet-resolution pipeline is inlined rather than split out, so it sits at 'some structure, could be better organized' rather than 4.	3 / 5
	Total	13 / 20 Passed

Description

66%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.

The description is specific and trigger-rich, clearly carving out a citation-audit niche. Its main weakness is the absence of an explicit 'Use when...' usage clause, leaving the 'when to use' guidance implicit.

Suggestions

Add an explicit 'Use when ...' sentence naming the situations that call for this skill (e.g. 'Use when auditing brain-page citations or resolving broken tweet/post references'), so completeness can reach 4-5.

Mention natural file/page synonyms (e.g. 'brain pages', 'notes', 'markdown pages') in the description to round out trigger-term coverage.

Tighten the version annotation ('Extended in v0.25.1') into the capability list without restating it, to avoid over-claiming and keep the description lean.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'Audit and fix citation formatting', 'scans for broken tweet/post references', 'resolves them via the host's X / Twitter API integration' — with only minor coverage gaps, fitting the 'lists several specific actions' anchor rather than the fully comprehensive level 5.	4 / 5
Completeness	It clearly states what the skill does but provides no explicit 'Use when...' clause — trigger timing is only weakly implied via the triggers list, and per the judging guidelines a missing 'Use when...' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Triggers like 'fix citations', 'fix broken citations', 'citation audit', 'check citations', 'citation fixer' give good natural-phrase coverage users would actually say, missing only a few synonyms/extensions, so level 4 fits better than 3 or 5.	4 / 5
Distinctiveness Conflict Risk	The citation-formatting / broken-tweet-resolution niche with its specific triggers is mostly distinct with only minor overlap risk against related editing skills, matching the 'mostly distinct' anchor rather than the fully minimal-conflict level 5.	4 / 5
	Total	15 / 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
relative_links	Relative link issues: 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: skills/citation-fixer/SKILL.md
Commit: 43597b1

Reviewed: 1 day 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.