CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

convex-hackathon-skill

Create and update an evidence-based hackathon.md build log for a Convex project. Use when a user invokes $convex-hackathon-skill, /convex-hackathon-skill, or /hackathon; mentions a Convex hackathon; asks to start, backfill, refresh, or correct a hackathon build log; or wants submission-ready project history. Work from local repository evidence, keep claims honest, exclude secrets and personal data, and never submit, deploy, or commit.

Quality

97%

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

92%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, well-structured instruction skill: an unambiguous two-action interpretation section, a seven-step workflow with a genuine idempotency checkpoint, concrete evidence and privacy rules, and a correctly scoped one-level reference verified to exist. Only minor trimming opportunities in a few redundant lines keep it from full marks on token efficiency.

DimensionReasoningScore

Conciseness

The body is directive with zero concept-explanation padding, but a few lines could be trimmed: "Do not require the user to know the start action" restates the intent of the preceding sentence, "Treat the file as a public, evidence-based build log" repeats the description, and a few evidence principles in "Use evidence carefully" overlap the reference's field rules. It is not a 3 because nothing explains concepts Claude already knows; not a 5 because these minor tokens do not all earn their place.

4 / 5

Actionability

Guidance is fully concrete and executable for an instruction-only skill: exact commands ("git rev-parse --show-toplevel"), exact paths ("references/log-format.md", "convex/convex.config.ts"), sentinel values ("not deployed", "none"), and explicit conditions covering Git vs. no-Git, start vs. update, and no-op runs. Specific rules cover the common cases.

5 / 5

Workflow Clarity

The seven numbered steps are clearly sequenced with an explicit validation gate ("Check idempotency before saving... leave the file unchanged"), fallback paths (Git root vs. workspace root), and a correction loop ("If local evidence conflicts with an existing claim, keep the evidence-based value and briefly flag the correction"). The destructive/batch cap does not apply since the skill edits only hackathon.md.

5 / 5

Progressive Disclosure

The body's single reference ("Read `references/log-format.md` before creating or editing `hackathon.md`") points to a real, one-level-deep bundle file, clearly signaled at the exact point of need. The split is appropriate: workflow and guardrails in SKILL.md, exact header/entry formats and the detection table in the reference, which itself opens with a Contents list for navigation.

5 / 5

Total

19

/

20

Passed

Description

100%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 model description: it states concrete capabilities on a specific artifact, gives an explicit "Use when" clause covering both invocation commands and natural-language variants, and locks itself to a distinct Convex-hackathon niche. The trailing guardrail sentences add behavioral boundaries without fluff or over-claiming.

DimensionReasoningScore

Specificity

"Create and update an evidence-based hackathon.md build log" plus "start, backfill, refresh, or correct a hackathon build log" names a concrete artifact and multiple specific actions with comprehensive coverage of the niche, matching the anchor-5 example's action list. It is not a 4 because there are no minor gaps in coverage of the skill's capabilities.

5 / 5

Completeness

The what is explicit ("Create and update an evidence-based hackathon.md build log for a Convex project") and the when is explicit with concrete trigger phrases ("Use when a user invokes...; mentions a Convex hackathon; asks to start, backfill, refresh, or correct a hackathon build log; or wants submission-ready project history"). This matches the anchor-5 example structure exactly.

5 / 5

Trigger Term Quality

Triggers span invocation forms ("$convex-hackathon-skill, /convex-hackathon-skill, or /hackathon"), natural phrases ("mentions a Convex hackathon", "submission-ready project history"), and synonyms ("start, backfill, refresh, or correct"). It is not a 4 because no natural phrasing a user would say in this niche is missing.

5 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche with domain-locked triggers ("Convex hackathon", "hackathon build log", "/hackathon"), mirroring the anchor-5 PDF example's pattern of distinct domain triggers. Overlap risk with generic documentation or logging skills is minimal.

5 / 5

Total

20

/

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

FacundoLucci/autonomous-buyer

Path

.agents/skills/convex-hackathon-skill/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.