CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

clinical-kb-workflow

Use when working in the verified PsychSift checkout, especially for local run, UI/browser QA, Supabase/OpenAI/RAG changes, clinical governance, dependency/upload shortcuts, or choosing verification.

Quality

66%

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/clinical-kb/skills/clinical-kb-workflow/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 dense, well-structured operational policy skill: nearly every section gives specific commands with explicit conditions, validation gates, and safety boundaries, and navigation to external policy docs is clearly signaled. The main weaknesses are inlined time-sensitive version pins and a few cryptic, non-actionable sentences that dilute token efficiency.

Suggestions

Move pinned versions and Supabase project refs (Next.js 16, React 19, sjrfecxgysukkwxsowpy) into a clearly labeled 'repo snapshot / verify before use' note or a reference file so stale constants don't penalize the evergreen guidance.

Replace cryptic hedges like 'A sanitized child process does not prove the raw host boundary accepted a selected legacy profile' with a concrete, actionable rule (what to check, what to do).

Add an explicit failure-recovery step to the Verification section (e.g. 'If the focused check fails, fix it and re-run before widening') to complete the validate-fix-retry loop.

DimensionReasoningScore

Conciseness

The body is mostly lean, directive bullets that assume competence, but it embeds time-sensitive version pins ('Next.js 16, React 19, npm 11, Node 24', two Supabase project refs) outside any deprecated/old-patterns section, and includes cryptic hedging sentences ('A sanitized child process does not prove the raw host boundary accepted a selected legacy profile') that could be tightened.

3 / 5

Actionability

Concrete, copy-paste-ready commands with clear when-to-use conditions ('npm run ensure', 'npm run verify:cheap', 'npm run verify:pr-local', 'npm run check:supabase-project' as an approval gate) cover the common cases, but a few gaps remain — the Next.js docs reference gives a directory rather than specific files, and several bullets are behavioral rather than executable.

4 / 5

Workflow Clarity

Each scenario has a clear sequence with explicit validation checkpoints and escalation rules ('run npm run ensure first, prove the affected journey', 'Start from the smallest failing check and widen only after the focused failure is resolved') plus approval gates for risky operations. It falls short of a 5 because there is no explicit error-recovery loop describing what to do when a check fails.

4 / 5

Progressive Disclosure

Well-organized sections with clearly signaled, one-level-deep references to policy docs ([verification-gates.md](../../../../docs/agents/verification-gates.md), codex-cloud-environment.md, smart-agent-allocation.md) and no buried or nested references. The ~64-line body keeps all content inline; slightly above the compact-skill threshold and material like the verification-gate decision table could live in a reference file, so it fits anchor 4 rather than 5.

4 / 5

Total

15

/

20

Passed

Description

51%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 highly distinctive, well-scoped trigger description that would reliably fire for the intended project, but it omits any statement of what the skill does. Adding an explicit capability statement alongside the 'Use when...' clause would substantially improve it.

Suggestions

Add an explicit 'what' statement of the skill's capabilities before the 'Use when' clause, e.g. 'Runs the local dev server, selects and executes verification gates, and enforces clinical-governance and API-cost safety rules for the PsychSift Next.js app.'

List 1-2 concrete actions the skill performs (e.g. 'runs npm run ensure and selects verification gates') so the description is not trigger-only.

Add a few natural synonyms users might say, such as 'tests', 'embeddings', or 'migrations', to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ('verified PsychSift checkout') and concrete sub-areas ('local run, UI/browser QA, Supabase/OpenAI/RAG changes, clinical governance'), but states no actions the skill actually performs, matching the anchor 'Names the domain but actions are minimal or generic'.

2 / 5

Completeness

The description is entirely a 'when' clause ('Use when working in the verified PsychSift checkout, especially for...') with the 'what' — what the skill does — completely absent, matching the anchor example 'Use when working with documents'. A clear 'what' would be required for a 3.

2 / 5

Trigger Term Quality

Good natural keyword coverage ('local run', 'UI/browser QA', 'Supabase', 'OpenAI', 'RAG', 'clinical governance', 'choosing verification') that users on this project would naturally say, though a few common variations (tests, migrations, embeddings) are missing.

4 / 5

Distinctiveness Conflict Risk

It is bound to a named, verified project checkout ('PsychSift') with distinct trigger areas (Supabase/OpenAI/RAG, clinical governance), giving it a clear niche with minimal risk of triggering for the wrong skill.

5 / 5

Total

13

/

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

relative_links

Relative link issues: 4 suspicious

Warning

Total

15

/

16

Passed

Repository

BigSimmo/PsychSift

Path

plugins/clinical-kb/skills/clinical-kb-workflow/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.