CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dev-implementation

AI DevKit · Implementation phase guidance for executing feature plans and checking implementation against design. Use when the user wants to implement planned tasks, update implementation docs, verify code matches design, or run dev-lifecycle phases 5 and 7.

Quality

84%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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-structured instruction-only skill: concrete commands, explicit sequencing, validation gates, and per-task documentation checkpoints with no filler or known-concept explanation. The residual gaps are a handful of high-level steps and implicit (rather than explicit) failure-handling loops around the lint gate.

DimensionReasoningScore

Conciseness

The body is dense and imperative with no explanations of concepts Claude already knows — every step is non-obvious process guidance (e.g., "Subtract before adding: delete dead paths, redundant guards, stale tests, and one-caller wrappers"). A few multi-sentence steps (reuse guidance, domain-modeling step) could be tightened slightly, placing it just below the lean-everywhere 5 anchor.

4 / 5

Actionability

It gives executable commands (`npx ai-devkit@latest lint --feature <name>`), explicit path resolution with fallback (`.ai-devkit.json` `paths.docs`, falling back to `docs/ai`), enumerated status values, and named sibling skills to load (`tdd`, `verify`, `dev-simplify`). As an instruction-only skill the absence of code is not penalized, but a few steps remain high-level direction ("Gather context", "Summarize design: key decisions, components, interfaces, data flows"), keeping it below fully copy-paste-ready 5.

4 / 5

Workflow Clarity

Both phases have clearly sequenced numbered steps with a preamble Phase Contract, a lint validation gate before work, per-task doc-update checkpoints, a blocked-status mechanism, and an after-section "ask if new tasks were discovered" feedback loop, plus explicit "Next:" phase transitions. It sits below the 5 anchor because some checkpoints are implicit (e.g., no explicit instruction on what to do when lint fails) rather than spelled-out validate-fix-retry loops.

4 / 5

Progressive Disclosure

This is a sub-50-line single-file skill with no bundle files, and the content is well-organized into clearly signaled sections (Phase Contract, Execute Plan, Check Implementation, Next). Per the rubric's simple-skill guidance, well-organized sections alone warrant a 5; cross-references to other lifecycle skills (dev-planning, dev-testing, dev-review) are appropriately one level deep.

5 / 5

Total

17

/

20

Passed

Description

83%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.

A strong description that explicitly covers both what the skill does and when to use it, with natural trigger phrases and concrete domain-scoped actions in third-person voice. Its only weaknesses are slight workflow-level abstraction in the action list and a few missing natural trigger synonyms.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "executing feature plans", "checking implementation against design", "update implementation docs", "verify code matches design" — in the AI DevKit domain, with only minor coverage gaps. It falls just below the comprehensive multi-action coverage of the 5 anchor because the actions are stated at a workflow level rather than as fully concrete capabilities.

4 / 5

Completeness

It clearly answers both: the "what" ("Implementation phase guidance for executing feature plans and checking implementation against design") and an explicit "when" with concrete trigger phrases ("Use when the user wants to implement planned tasks, update implementation docs, verify code matches design, or run dev-lifecycle phases 5 and 7"). This matches the 5 anchor's explicit what-and-when with concrete triggers; it is not the 4 anchor since the 'when' clause is specific rather than needing more detail.

5 / 5

Trigger Term Quality

The "Use when" clause surfaces natural phrases users would say — "implement planned tasks", "update implementation docs", "verify code matches design" — plus specific phase triggers. A few natural variations (e.g., "execute the plan", "build the feature") are missing, keeping it below the comprehensive synonym coverage of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The skill is scoped to the AI DevKit lifecycle and specific phases (5 and 7), making it mostly distinct from sibling phases (dev-planning, dev-testing, dev-review) with clear niche triggers. Minor overlap risk remains with generic implementation/coding skills triggered by "implement planned tasks", keeping it below the 5 anchor's minimal-conflict profile.

4 / 5

Total

17

/

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

codeaholicguy/ai-devkit

Path

skills/dev-implementation/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.