CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ecc-contribution-review

Prepare an ECC skill contribution for review by organizing repository, install-surface, cross-harness, validation, security, and commit observations into a local proposal. Use when preparing a skill contribution for review.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/ecc-contribution-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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 content is a tight, well-sequenced workflow with copy-paste commands, explicit exit-code validation, and recompile feedback loops. Its main defects are bundle references that do not resolve (docs/WORKFLOW.md, docs/DESIGN.md, and the referenced template/script paths) and repeated compiler-disclaimer statements that could be consolidated.

Suggestions

Ship docs/WORKFLOW.md and docs/DESIGN.md in the bundle (or remove/inline those links) so the referenced navigation paths resolve.

Include the referenced template and compile script (templates/contribution-review-observation.json, scripts/compile_contribution_review.py) in the bundle, or state where they live relative to the checkout.

Consolidate the four repeated compiler-disclaimer statements into a single "What the compiler does not do" note to reduce token overhead.

DimensionReasoningScore

Conciseness

The body is lean with no explanations of known concepts, but the compiler's non-responsibility is restated roughly four times ("it does not independently inspect Git, files, CI, test results, coverage, or referenced evidence"; "The compiler does not execute them"; "It does not prove that supplied claims are true or CI passed"; "never approves a contribution") — minor over-explanation that could be consolidated, matching anchor 4 rather than the every-token-earns-its-place anchor at 5.

4 / 5

Actionability

The compile step is fully executable ("mkdir -p .memory-kit", "cp skills/ecc-contribution-review/templates/... ", "python3 skills/ecc-contribution-review/scripts/compile_contribution_review.py ... --output ...") with explicit exit-code semantics ("Exit code 0 means a packet was emitted... Exit code 2 means validation faults"). However, steps 1-4 direct recording observations without any gathering commands, and the referenced template/script paths are absent from the bundle, matching "mostly executable guidance with minor gaps" rather than the fully copy-paste-ready anchor at 5.

4 / 5

Workflow Clarity

Seven clearly numbered steps include explicit validation checkpoints ("Run the required validators and tests separately. Record exact commands, results, and evidence"; "Review every reported contradiction and semantic page fault"; exit codes 0/2 with "Inspect the packet and stderr") and a recompile feedback loop ("Recompile after changes to HEAD, policy, manifests, catalog, adapters, tests, coverage, security findings, or review evidence") — matching the anchor 5 pattern of explicit validation with error-recovery loops. It is not 4 because validation and recovery are explicit rather than implied.

5 / 5

Progressive Disclosure

The body is a concise overview with clearly signaled one-level-deep references ("See [the workflow](docs/WORKFLOW.md), [the design](docs/DESIGN.md), and [the contract](references/contribution-review-contract.md)"), but only references/contribution-review-contract.md actually exists in the bundle — docs/WORKFLOW.md and docs/DESIGN.md are absent, so two of three references dead-end. Scoring against the actual bundle structure, unresolved references are more than a minor organization gap, keeping this at anchor 3 rather than 4.

3 / 5

Total

16

/

20

Passed

Description

62%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 clearly states what the skill does and includes an explicit "Use when" clause, with a distinct niche. Its weaknesses are a circular, narrow trigger clause and single-verb capability framing that limits trigger-term coverage and specificity.

Suggestions

Replace the circular when-clause with concrete trigger phrases, e.g. "Use when the user asks to compile, review, or submit an ECC skill contribution, or mentions a contribution review packet or PR."

Add natural synonym terms users would actually say (e.g., "submit", "propose", "pull request", "ECC") to broaden trigger coverage beyond "preparing a skill contribution for review".

State one or two additional concrete actions (e.g., "compile a review packet" and "flag contradictions for maintainer review") so capability coverage reads as several specific actions rather than one.

DimensionReasoningScore

Specificity

"Prepare an ECC skill contribution for review by organizing repository, install-surface, cross-harness, validation, security, and commit observations into a local proposal" names the domain plus a single concrete action (organizing observations into a proposal) with enumerated observation categories, but does not list several distinct actions, matching the 1-2-concrete-actions anchor rather than the several-actions anchor at 4.

3 / 5

Completeness

Both parts are explicit: the what ("organizing repository, install-surface, cross-harness, validation, security, and commit observations into a local proposal") and the when ("Use when preparing a skill contribution for review"). The when-clause is present but largely restates the what and could be more specific, matching anchor 4 rather than the concrete-distinct-trigger-phrases anchor at 5.

4 / 5

Trigger Term Quality

Relevant keywords like "skill contribution" and "review" are present, but common natural variations a user might say ("submit", "propose", "pull request", "ECC") are missing, and terms like "install-surface" and "cross-harness" are jargon users would not naturally utter — matching the "some relevant keywords but missing common variations or synonyms" anchor.

3 / 5

Distinctiveness Conflict Risk

The ECC skill-contribution-review niche is clear and unlikely to trigger unrelated skills, but the when-clause omits "ECC", leaving minor overlap risk with generic contribution-review or code-review skills — "mostly distinct; minor overlap risk" at 4 rather than the minimal-conflict anchor at 5.

4 / 5

Total

14

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 2 possibly missing (docs/DESIGN.md, docs/WORKFLOW.md)

Warning

Total

14

/

16

Passed

Repository

affaan-m/ECC

Path

.agents/skills/ecc-contribution-review/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.