export-open-issues

Audit and export open issues from any project tracker with summary analysis and vault archival

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/export-open-issues/SKILL.md

Quality

Content

72%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 content is highly actionable with executable commands for every supported tracker and a clear phased sequence, but it is a monolithic batch workflow lacking inline validation checkpoints and with no external reference structure. Adding validation steps and splitting out the report template would address the two weakest dimensions.

Suggestions

Insert an explicit validation checkpoint between Phase 1 and Phase 2 — e.g. verify issue counts, flag empty/partial collector returns, and confirm all active trackers responded before analyzing — to satisfy the batch-operation feedback-loop requirement.

Move the large Phase 3 report template into a separate `references/report-template.md` and reference it one level deep, improving progressive disclosure and trimming the main file.

Add a retry/fix loop inline in Phase 1 (not only in the Fallback table) so a failed collector is re-run before proceeding to analysis.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable templates and commands with little over-explanation of concepts Claude already knows; it assumes competence. It is below 5 because the large inline report template and per-tracker agent prompts could be trimmed or externalized, leaving minor padding.	4 / 5
Actionability	Provides copy-paste-ready, executable guidance across all common cases — `gh issue list --repo ... --json ...`, a concrete JQL query, and real Linear MCP tool names (`mcp__claude_ai_Linear_2__list_issues`, etc.). Placeholders like `[CUSTOMIZE: your-org/your-repo]` are expected customization, not gaps, so it meets the fully-executable anchor.	5 / 5
Workflow Clarity	Phases 1–5 are clearly sequenced with a pre-flight check, but this is a batch operation (export up to 500 issues) and the main flow lacks inline validation checkpoints — verification lives only in the separate Fallback/Error tables. Per the judging guidelines, a batch skill without explicit validate-then-proceed steps is capped at 3.	3 / 5
Progressive Disclosure	Sections are well-organized with clear phase headers, but the skill is a single monolithic file with no bundle files and no one-level-deep references; the large report template and collector prompts are inlined content that could live in separate files. The under-50-line simple-skill exception does not apply to this ~300-line skill, so it sits at 3 rather than higher.	3 / 5
	Total	15 / 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 states a clear, multi-action purpose with reasonable natural keywords and a distinct niche, but it omits any explicit 'Use when' trigger guidance, which caps its completeness. Adding a trigger clause would raise the strongest remaining weakness.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user wants to audit open issues, run a backlog audit, or export an issue report for sprint planning or stakeholder reporting.'

Add natural synonyms users say — 'backlog', 'issue report', 'sprint/cycle planning' — to broaden trigger coverage.

Specify the analysis types concretely (e.g. 'aging/staleness, priority distribution, assignee load') instead of the generic 'summary analysis'.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'Audit and export open issues', 'summary analysis', 'vault archival' — giving good coverage with minor gaps (analysis types are not enumerated). It is below 5 because 'summary analysis' is somewhat generic rather than a fully specified concrete action.	4 / 5
Completeness	Has a clear 'what' ('Audit and export open issues from any project tracker with summary analysis and vault archival') but no 'Use when...' clause or explicit trigger guidance. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains natural terms a user would say — 'open issues', 'export', 'project tracker' — but misses common variations like 'backlog', 'issue report', or 'sprint'. It is above 3 because multiple relevant natural keywords are present, but below 5 because synonyms users actually say are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (open-issues audit/export with vault archival) with distinct triggers, but 'any project tracker' spans GitHub/Linear/Jira and carries minor overlap risk with tracker-specific skills. It is below 5 because of that breadth, above 3 because the niche is well-defined.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: huytieu/COG-second-brain
Path: .claude/skills/export-open-issues/SKILL.md
Commit: cb4644d

Reviewed: 2 days 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.