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

72%

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

77%

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

The content is highly actionable and the workflow is clearly sequenced with real verification checkpoints, but it is somewhat verbose due to inline version history and could split its detailed tweet-resolution pipeline into a reference file for cleaner progressive disclosure.

Suggestions

Move the version-history framing (repeated '(v0.25.1)' tags and 'Extended in v0.25.1') into a dedicated changelog/deprecated section to remove time-sensitive noise from the main flow.

Extract the detailed 5-step tweet-resolution pipeline into a bundle reference file (e.g. references/tweet-resolution.md) and keep a concise pointer in the body to improve progressive disclosure.

Tighten descriptive prose such as 'short, punchy, often starts with a quote' into concrete detection patterns to further improve conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable bash, query patterns, and before/after templates, but repeated (v0.25.1) version tags and mildly padded prose (e.g. 'short, punchy, often starts with a quote') add noise that could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance — a bash candidate-finding loop, exact X API query strings, deterministic URL construction, and concrete before/after citation templates.	3 / 3
Workflow Clarity	The 5-step tweet-resolution pipeline is clearly sequenced with an explicit verification checkpoint at Step 4, plus batch-commit recovery and rate-limiting guidance for the batch/mutating operations.	3 / 3
Progressive Disclosure	Sections are well organized, but the ~160-line body keeps the full tweet-resolution pipeline inline (content that could be a separate reference), and its external path references point outside the skill bundle rather than to bundle-internal one-level-deep files.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 clearly distinct, but it omits an explicit 'Use when...' activation clause and keeps its best trigger terms in the frontmatter rather than the description body. Adding a usage trigger line would raise both completeness and trigger-term quality.

Suggestions

Append an explicit activation clause such as 'Use when fixing citation formatting or resolving broken tweet/post references on brain pages' to satisfy the completeness 'when' requirement.

Weave the natural trigger phrases (e.g. 'fix citations', 'citation audit') into the description body so users who say those words activate the skill from the description alone.

Drop or relocate the 'Extended in v0.25.1' version note from the description; version history is time-sensitive and adds noise without aiding activation.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Audit and fix citation formatting', 'scans for broken tweet/post references', 'resolves them via the host's X / Twitter API integration' — rather than vague domain naming.	3 / 3
Completeness	Clearly answers what the skill does, but there is no 'Use when...' clause or equivalent explicit guidance for when Claude should activate it, which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Contains relevant natural terms ('citation formatting', 'broken tweet/post references') but the strongest user-facing trigger phrases ('fix citations', 'citation audit') live in the frontmatter triggers list, not in the description body itself, leaving common variations uncovered.	2 / 3
Distinctiveness Conflict Risk	The combination of brain-page citation auditing and deterministic tweet-URL resolution is a distinct niche with specific triggers, unlikely to collide with unrelated skills.	3 / 3
	Total	10 / 12 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: 3fafb69

Reviewed: about 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.