work-issues
Autonomously work one task from an issues/ queue end-to-end — explore, implement (TDD when applicable), run feedback loops, commit, update the issue file. Step 3 of the build pipeline (write-a-prd → prd-to-issues → work-issues). Heavyweight (commits code, modifies the issue queue); explicit invocation only. Headless loop runner: bin/loop.sh. Triggers: /work-issues, "work the issue queue", "run an AFK iteration", "do one issue end-to-end".
79
100%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates what the skill does (autonomously works tasks from an issue queue through a full cycle of explore, implement, test, commit, and update), when to use it (with explicit trigger phrases and pipeline context), and how it fits into a broader workflow. It uses third-person voice appropriately and provides enough specificity and distinctiveness to avoid conflicts with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: explore, implement with TDD, run feedback loops, commit, update the issue file. Also specifies its place in a pipeline (step 3) and mentions the headless loop runner script. | 3 / 3 |
Completeness | Clearly answers both 'what' (autonomously work a task from the issues queue end-to-end with specific sub-actions) and 'when' (explicit triggers listed, pipeline context given, and notes it requires explicit invocation only). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: '/work-issues', 'work the issue queue', 'run an AFK iteration', 'do one issue end-to-end'. These are specific and varied enough to cover likely user phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: working issues from a queue in a specific build pipeline. The explicit invocation requirement, pipeline step number, and specific triggers like '/work-issues' and 'AFK iteration' make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that serves as a clear, concise autonomous workflow specification. It efficiently communicates a complex multi-step process with explicit validation checkpoints, concrete commands, and well-defined guardrails. The hard rules section and done-check sentinel pattern show thoughtful design for headless operation safety.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of what TDD is, what git does, or how testing frameworks work. The skill assumes Claude's competence throughout and only provides project-specific workflow rules and conventions. | 3 / 3 |
Actionability | Concrete bash commands for gathering context, specific framework-by-framework feedback loop commands, explicit commit message requirements with enumerated fields, and clear file operations (move to issues/done/). The guidance is specific and directly executable. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced: gather inputs → done check → select task → explore → implement → feedback loops → commit → rubric check → issue housekeeping. Validation checkpoints are explicit (don't commit a red build, feedback loops before committing), with error recovery guidance (note unrelated failures, stop on unexpected repo state). Hard rules provide clear guardrails. | 3 / 3 |
Progressive Disclosure | The skill is well-structured with clear section headers that serve as a navigable overview. It references the `tdd` skill for TDD work and `prd-to-issues` for upstream context without inlining their content. For a standalone skill with no bundle files, the organization is appropriate and sections are right-sized. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- belchman/claude-skills
- Commit
be88d6c
- Reviewed
Table of Contents
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.