CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

implement

Implement a piece of work based on a spec or set of tickets.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/implement/SKILL.md

The canonical home for this skill is implement in mattpocock/skills

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A lean, well-sequenced instruction skill that assumes Claude's competence and delegates repo-specific detail appropriately. Its main gap is the absence of an explicit failure/retry checkpoint before committing, and slightly loose quantifiers ('regularly', 'where possible').

Suggestions

Add an explicit validation gate before committing, e.g. "If the full suite fails, fix and re-run before proceeding to /code-review — commit only when it passes."

Tighten "Run typechecking regularly" to a concrete cadence or trigger, e.g. "Run typechecking after each module change and the full test suite once at the end."

Clarify the fallback for "Use /tdd where possible, at pre-agreed seams" — state what to do when a seam was not pre-agreed (e.g. write characterization tests first or proceed without TDD and note it).

DimensionReasoningScore

Conciseness

Eight lean lines with zero padding and no explanations of concepts Claude already knows — "Use /tdd where possible, at pre-agreed seams" assumes competence; every token earns its place.

5 / 5

Actionability

Concrete directives throughout ("Use /tdd", "run typechecking regularly, single test files regularly, and the full test suite once at the end", "use /code-review", "Commit your work to the current branch"), but "regularly" and "where possible" leave the cadence and scope slightly unresolved — 'mostly executable guidance with minor gaps'.

4 / 5

Workflow Clarity

The sequence (implement test-first → continuous checks → full suite at the end → /code-review → commit) is clear with checkpoints present, but there is no explicit failure-handling loop such as 'fix failures before committing' — 'clear sequence with most checkpoints present; minor validation gaps'.

4 / 5

Progressive Disclosure

An under-50-line, single-purpose skill with no external references needed: the flat imperative list reads in order, nothing is buried, and no content exists that belongs in a separate file — the simple-skill exception applies.

5 / 5

Total

18

/

20

Passed

Description

45%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 names its domain (implementing work from a spec or tickets) but the action verb is generic and the 'when to use' half is entirely absent. Without a 'Use when...' clause or trigger phrases, it will not reliably surface when users need it and risks overlapping with general implementation requests.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases, e.g. "Use when the user asks to implement a spec, a set of tickets, or a feature described in a requirements document or issue tracker."

Replace the vague "a piece of work" with the concrete actions the skill performs, e.g. "Implement the work described in a spec or tickets: write code test-first, run typechecks and tests, review, and commit."

Broaden trigger vocabulary with natural synonyms users would say — "spec", "tickets", "requirements", "user stories", "issue", "feature request" — to improve both trigger term quality and distinctiveness.

DimensionReasoningScore

Specificity

"Implement a piece of work" is a generic action phrase; "based on a spec or set of tickets" names the domain but the action remains minimal, matching the anchor 'Names the domain but actions are minimal or generic' (e.g. 'Processes PDF files').

2 / 5

Completeness

The 'what' is stated ("Implement a piece of work based on a spec or set of tickets") but there is no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

"spec" and "set of tickets" are natural terms a user would say, but common variations and synonyms (requirements, user stories, feature request, backlog) are missing — 'Some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

"Implement a piece of work" alone would collide with nearly any coding skill, but the spec/tickets qualifier narrows the niche to 'somewhat specific but could still overlap with similar skills' — a general build/feature request could still route here.

3 / 5

Total

11

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

tonykay/transcriber

Path

.agents/skills/implement/SKILL.md

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.