CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-against-solid-principles

Ensemble SOLID review — fans the ruleset across overlapping focused workers over the same code, then reduces by corroboration.

58

Quality

73%

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 ./examples/solid-review-ab/multi-low-intelligence-focused-agents/.claude/skills/review-against-solid-principles/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%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 tight, highly actionable orchestration body with real commands and a clear three-phase sequence. Its one substantive weakness is the absence of validation between the parallel map step and the reduce step, which the batch-operation guideline caps at 3 for workflow clarity.

Suggestions

Add a checkpoint between Map and Reduce, e.g. 'Before reducing, verify every worker outfile in ./findings/workers/ exists and matches the candidate schema; re-run or re-prompt any missing worker.'

Provide a short worker prompt template so the map step is fully copy-paste ready rather than a list of ingredients.

State the expected outcome of each command (planner emits worker assignment + keep-threshold; reduce emits ranked findings) so failures are detectable at each phase.

DimensionReasoningScore

Conciseness

The body is lean and entirely operational: fixed paths, two commands, and worker-assignment instructions, with no explanation of concepts Claude already knows. Even the wordiest passage (resolving the ensemble scripts path, 'the runner may pass an absolute path instead — use whichever it provides') is necessary operational detail, not padding, matching 'every token earns its place'.

5 / 5

Actionability

Two concrete `uv run` commands with real arguments ('--report-dir "$(pwd)/findings/workers" --window 2 --json', "--keep-threshold 2") are executable, and worker spawn instructions list exact inputs (groups, rules, targets, outfile, location format). Minor gaps keep it below 5: the `<scripts>` placeholder must be resolved by the reader, and the map step gives worker-prompt ingredients rather than a copy-paste prompt template. It is above 3 because the guidance is genuinely executable, not pseudocode.

4 / 5

Workflow Clarity

The Plan → Map → Reduce sequence is clearly numbered and labeled deterministic vs. parallel, but the batch map step (one worker agent per group, run in one parallel batch) has no explicit validation checkpoint — e.g., verifying each worker's outfile exists and is well-formed before reducing. Per the judging guidelines, batch operations without validation cap workflow clarity at 3, matching 'sequence present but checkpoints missing or implicit'.

3 / 5

Progressive Disclosure

The skill is under 50 lines, has no bundle files of its own, and is well organized (a fixed-paths list followed by numbered steps). Its only external dependency (the ensemble scripts) is referenced one level deep with an explicit path ('../../../plugins/plugin-creator/skills/ensemble-rule-review/scripts/'). Per the simple-skill exception, this can score 5 with just well-organized sections.

5 / 5

Total

17

/

20

Passed

Description

53%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 and reasonably specific 'what' with distinctive ensemble terminology, but completely omits any 'when to use' trigger guidance and offers only a single natural keyword. Adding an explicit trigger clause with common synonyms would lift specificity, completeness, and trigger-term quality together.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks for a SOLID review, review against SOLID principles, or a design-principles review of Python code.'

Add natural keyword variations such as 'SOLID principles', 'single responsibility', 'open/closed', and 'design principles review' so users' phrasings match.

Consider naming the concrete actions users care about (parallel worker review, corroboration, ranked findings) rather than only the fan/reduce mechanics.

DimensionReasoningScore

Specificity

The description names the domain ("Ensemble SOLID review") and two concrete process actions ("fans the ruleset across overlapping focused workers over the same code", "reduces by corroboration"), but does not enumerate a comprehensive list of specific actions. It matches the anchor for naming a domain with 1-2 concrete actions, falling short of the several-actions coverage of a 4.

3 / 5

Completeness

The 'what' is clearly stated (ensemble SOLID review via fan-out workers and corroboration-based reduction), but there is no 'Use when...' clause or any equivalent trigger guidance. Per the judging guidelines, a missing 'when' caps completeness at 3.

3 / 5

Trigger Term Quality

"SOLID review" is a natural phrase a user would say, but the description includes no synonyms or variations such as "SOLID principles", "design principles", or "code review". This matches 'some relevant keywords but missing common variations or synonyms'; it is above a 2 (a domain-relevant natural term exists) but below a 4 (coverage is thin).

3 / 5

Distinctiveness Conflict Risk

"Ensemble SOLID review" occupies a fairly distinct niche — the ensemble fan/reduce mechanism distinguishes it from generic review skills. However, it could still overlap with a plain SOLID-principles review or general code-review skill since no distinct trigger phrases disambiguate it, matching 'mostly distinct; minor overlap risk'.

4 / 5

Total

13

/

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

Jamie-BitFlight/claude_skills

Path

examples/solid-review-ab/multi-low-intelligence-focused-agents/.claude/skills/review-against-solid-principles/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.