CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

implement

Implement a feature or fix with automatic validation

Quality

65%

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 ./plugins/pragma/skills/implement/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 strong, highly executable multi-phase workflow with outstanding validation checkpoints and feedback loops. Its weaknesses are repetition of the commit-mode rules across phases and the absence of any progressive disclosure: all detail is inlined in one long file rather than split into reference files.

Suggestions

State the commit-mode rules once in Phase 1 and have Phases 2, 3, and the Rules section reference them by name instead of restating the green/readable/no-commits behavior each time.

Move stable, bulky detail — the Phase 0 fallback baseline procedure, the validator dispatch list, and the commit-mode case analysis — into reference files under references/ and link to them, shortening SKILL.md to the orchestration overview.

Fix the TypeScript lint fallback: 'npx --no biome check .' is not valid npx syntax, and the 'pnpm run lint or npx ...' construction leaves the choice between the two commands ambiguous — pick one deterministic fallback order.

DimensionReasoningScore

Conciseness

The body is dense procedural instruction rather than padded background, but the commit-mode rules settled in Phase 1 Step 5 are restated at length across Phases 2, 3, and the final Rules section (e.g. 'the mode settled in Phase 1 Step 5', 'Every change this phase makes is committed under the mode from Phase 1 Step 5'), and inline justifications repeat earlier points. This matches 'Mostly efficient but includes some unnecessary explanation or could be tightened' rather than the minor-trim level (4).

3 / 5

Actionability

Guidance is largely executable: exact glob patterns ('.claude/rules/*.md'), concrete paths ('$PLUGIN_ROOT/claude-md/universal/base.md'), copy-paste commands ('golangci-lint run --fix -v', 'uv run pre-commit run --all-files', 'GIT_SEQUENCE_EDITOR=true git rebase -i --autosquash <base>'), and a full output template. Minor gaps keep it below fully-executable: the odd 'npx --no biome check .' syntax and the unresolved 'pnpm run lint or npx --no biome check .' choice.

4 / 5

Workflow Clarity

A clearly sequenced Phase 0→4 pipeline with explicit validation gates at every level: mandatory Phase 0 gate, per-unit checks under green commits, Phase 3 fix-and-re-validate loops, re-checks for new directories, failure escalation ('If stuck in a validation loop (3+ attempts), report the issue'), and stop-and-ask rules for failed commits. This matches 'Clear sequence with explicit validation steps; feedback loops for error recovery; checklists for complex processes'.

5 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), so everything lives inline in a ~370-line SKILL.md. Section headers organize it well, but self-contained content that plausibly belongs in separate reference files — the commit-mode rules, the Phase 0 fallback baseline procedure, the validator dispatch list — is inlined, matching 'Some structure but could be better organized; content that should be separate is inline'.

3 / 5

Total

15

/

20

Passed

Description

46%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 domain and a rough what, but omits any when-to-use guidance and lacks distinctive triggers. It reads as a generic implementation skill and would compete with many other coding skills for the same requests.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases, e.g. 'Use when the user asks to implement a feature, fix a bug, or make a code change that should be validated before completion.'

Expand the what with 2-3 more specific actions, e.g. 'loads project rules, plans commit units, runs linters and semantic validators, and commits in reviewable units'.

Differentiate from generic coding skills by naming the skill's distinct hook, e.g. mentioning the mandatory rule-injection and validation phases that set it apart from plain implementation.

DimensionReasoningScore

Specificity

"Implement a feature or fix with automatic validation" names the domain (feature/fix implementation) and 1-2 actions (implement, validate), matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. It is not a list of several specific actions (4) and is more than a bare domain claim (2).

3 / 5

Completeness

The "what" is stated (implement a feature or fix with automatic validation) but there is no "Use when..." clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3; this matches the anchor 'Has a clear what but when is missing or only weakly implied'.

3 / 5

Trigger Term Quality

Terms like "implement", "feature", and "fix" are natural phrases users say, but common variations and synonyms ("add", "build", "bug", "make a change") are absent, matching 'Some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

"Implement a feature or fix" is very broad and would overlap with virtually any coding or implementation skill; only "with automatic validation" offers slight differentiation. This fits 'Very broad; high overlap risk with many similar skills' better than the entirely-generic anchor (1) or the somewhat-specific anchor (3).

2 / 5

Total

11

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

peteski22/agent-pragma

Path

plugins/pragma/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.