CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

convex-deploy-guard

Classify + announce the target Convex deployment before any deployment-affecting command; fresh explicit consent for prod actions; session read-only mode.

Quality

79%

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 ./.agents/skills/convex-deploy-guard/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 an exemplary instruction-only guard: exact flags, commands, env vars, and a verbatim announce format, with a clearly sequenced workflow containing validation checkpoints and a diagnosis feedback loop. Its one weakness is token efficiency — the Rules section substantially duplicates the Workflow steps and could be collapsed into the invariants that add new information.

Suggestions

Collapse Rules bullets that restate Workflow steps 3–6 verbatim (MCP flag split, read-only, wrong-deployment) and keep only the invariants that add new framing ("per-action, per-target, per-session") or new information (the composition rule naming ship, env, migrate, seed).

Trim the motivational intro ("Deployments are not interchangeable, and most incidents start with a command aimed at the wrong one") to a single clause, since Claude can infer the motivation from the guard's existence.

DimensionReasoningScore

Conciseness

The body is telegraphic and dense, but the Rules section restates Workflow steps 3–6 nearly verbatim (e.g., the MCP-flag rule duplicates step 4, the read-only rule duplicates step 5), roughly 30% duplicated content — matching anchor 3 ("could be tightened") rather than anchor 4's "minor instances of over-explanation".

3 / 5

Actionability

Fully concrete, executable guidance: exact env vars and files to read (CONVEX_DEPLOYMENT in .env.local, convex.json, CONVEX_DEPLOY_KEY), exact commands (npx convex run --prod), exact MCP flags (--cautiously-allow-production-pii, --disable-tools run,envSet,envRemove), and a verbatim announcement format ("target: dev (joyful-capybara-123, personal dev)") — a match for anchor 5.

5 / 5

Workflow Clarity

The 7-step sequence has explicit validation checkpoints ("If two sources disagree, resolve before proceeding", fresh-consent gate, "Ambiguity = stop ... never guess") plus an error-recovery feedback loop ("do NOT re-deploy harder. Re-run step 1"), matching anchor 5; the destructive-operation cap does not apply because validation is present.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files and no need for external references, and its sections (Workflow, Rules) are well-organized — per the rubric's simple-skill guideline this scores 5 on structure alone.

5 / 5

Total

18

/

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 is specific, third-person, and tightly scoped to a distinct Convex deployment niche, but it lacks an explicit "Use when..." trigger clause and natural trigger synonyms, capping completeness and trigger-term quality. Adding concrete invocation triggers (e.g., "Use when running npx convex deploy, deploying to production, or the user says read-only") would raise both dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use before running npx convex deploy, npx convex run, or any command the user says targets production/preview/dev", to lift completeness from 3.

Include natural user phrasings and synonyms — "deploy", "production", "preview", "convex deploy" — alongside "prod" and "deployment" to improve trigger-term coverage.

Optionally name one or two more capabilities (MCP prod-flag discipline, wrong-deployment diagnosis) to close the specificity gap toward comprehensive coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Classify + announce the target Convex deployment", "fresh explicit consent for prod actions", "session read-only mode" — but coverage has minor gaps (no mention of MCP flag discipline or wrong-deployment diagnosis), so it matches anchor 4 rather than the comprehensive anchor 5.

4 / 5

Completeness

The "what" is clear (classify/announce targets, gate prod on fresh consent, enforce read-only mode), but there is no "Use when..." clause or equivalent explicit trigger guidance — "before any deployment-affecting command" only weakly implies when to invoke, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Contains relevant keywords ("Convex deployment", "prod", "read-only") but misses the natural phrases and variations users would say, such as "deploy", "npx convex deploy", "production", or "preview", matching anchor 3 (some relevant keywords, missing common variations) rather than the good-coverage anchor 4.

3 / 5

Distinctiveness Conflict Risk

"target Convex deployment" carves out a clear platform-specific niche with distinct triggers (deployment commands, prod consent, read-only mode), giving minimal conflict risk with any other skill — a direct match for anchor 5.

5 / 5

Total

15

/

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

openclaw/clawhub

Path

.agents/skills/convex-deploy-guard/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.