CtrlK
BlogDocsLog inGet started
Tessl Logo

to-issues

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.

68

0.95x
Quality

74%

Does it follow best practices?

Impact

80%

0.95x

Average score across 1 eval scenario

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/to-issues/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 a tight, well-structured instruction skill with a clear process, validation checkpoint via the user quiz, and a reusable issue template. Its only real gap is the absence of an explicit post-publish verification loop for the batch issue-creation step.

Suggestions

Add an explicit verification step after publishing (e.g. confirm each issue was created with the correct triage label and correct 'Blocked by' references).

Consider extracting the <issue-template> and <vertical-slice-rules> blocks into references/ to keep the main body as a pure overview.

Specify how to resolve the triage label vocabulary if /setup-matt-pocock-skills has not been run, so the skill is self-sufficient.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence throughout — no padding, no explanation of basic concepts, and every line earns its place.

5 / 5

Actionability

Provides a concrete 5-step process, a literal issue-template, and specific quiz prompts; as an instruction-only skill the guidance is actionable, with only minor gaps (e.g. how to format/label the triage label is left to setup).

4 / 5

Workflow Clarity

The numbered process is clearly sequenced with a quiz-and-iterate checkpoint before publishing, but the batch publish step lacks an explicit post-publish verification/validation loop.

4 / 5

Progressive Disclosure

Content is well-organized into clear sections with an inline one-level template; no bundle files exist, and structure is clean, though a couple of sections (slice rules, template) could optionally live in references.

4 / 5

Total

17

/

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 conveys a clear, specific purpose with good domain vocabulary but lacks any 'Use when...' trigger guidance, which limits its completeness. It is mostly distinct and only mildly held back by missing natural trigger phrasings.

Suggestions

Append a 'Use when ...' clause naming concrete triggers, e.g. 'Use when breaking a plan, spec, or PRD into issue-tracker tickets for AFK agents.'

Add common synonyms a user might say, such as 'split a PRD into tickets' or 'decompose a spec into tasks'.

Consider explicitly contrasting horizontal vs. vertical slicing in the trigger phrasing to reinforce distinctiveness.

DimensionReasoningScore

Specificity

Names the domain ('plan, spec, or PRD') and a concrete action ('Break ... into independently-grabbable issues ... using tracer-bullet vertical slices'), but the action framing stays somewhat abstract rather than enumerating multiple distinct operations.

4 / 5

Completeness

Clearly states what the skill does but provides no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Includes natural terms a user would say ('plan, spec, or PRD', 'issue tracker') alongside the more technical 'tracer-bullet vertical slices'; a few common synonyms or trigger phrasings are missing.

4 / 5

Distinctiveness Conflict Risk

The tracer-bullet/vertical-slice framing carves a distinct niche with low overlap risk, though it could be sharpened against generic issue-creation skills.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
coder/agent-tty
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.