CtrlK
BlogDocsLog inGet started
Tessl Logo

workspace-surface-audit

Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.

67

Quality

81%

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

75%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 a well-structured, actionable audit playbook with clear phases and a concrete output contract. It is efficient but carries minor redundancy and lacks explicit validation checkpoints and external reference files.

Suggestions

Deduplicate the three-way surface split: state it once in 'Output Format' and reference it from 'Non-Negotiable Rules' rather than restating.

Add an explicit verification step in the audit process (e.g., 'confirm each recommended ECC shape maps to a real gap surfaced in Phase 1 or 2') to push workflow clarity toward 5.

Consider moving the detailed Recommendation Rules or Audit Inputs into a references/ file so the SKILL.md overview stays leaner and progressive disclosure can score 5.

DimensionReasoningScore

Conciseness

The body is lean and well-sectioned with bullets and a table, but the three-way 'already available / not wrapped / missing' split is restated across 'Non-Negotiable Rules' and 'Output Format', and 'Good Outcomes' partly echoes the output spec—minor trimming opportunities keep it below 5.

4 / 5

Actionability

Concrete inputs (package.json, .mcp.json, .claude/settings*.json, key names like STRIPE_API_KEY), a gap-to-shape decision table, and a fixed five-section output format give mostly executable guidance; it lacks runnable commands, but as an instruction-only audit skill the guidance is specific enough to land at 4 rather than 3.

4 / 5

Workflow Clarity

Three clearly sequenced phases (Inventory, Benchmark, Turn Gaps Into Decisions) with sub-steps form a clear sequence; the read-only nature means the destructive/batch cap does not apply, but no explicit validation or verification checkpoint keeps it below 5.

4 / 5

Progressive Disclosure

No bundle files exist and the single ~120-line file is well-organized with clear headers; it exceeds the under-50-line simple-skill exception, so minor inlining of content that could live in references keeps it at 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

88%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 strong: concrete actions, an explicit 'Use when' trigger, and a distinctive ECC-native positioning. The only gap is slightly limited trigger-term variety.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across two verbs—'Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup' and 'recommend the highest-value ECC-native skills, hooks, agents, and operator workflows'—giving comprehensive coverage rather than the minor gaps of a 4.

5 / 5

Completeness

Explicitly answers both what (audit surfaces, recommend ECC-native shapes) and when ('Use when the user wants help setting up Claude Code or understanding what capabilities are actually available'), matching the anchor for concrete trigger phrases.

5 / 5

Trigger Term Quality

'setting up Claude Code' and 'what capabilities are actually available' are natural user phrases, but coverage stops at two scenarios without synonyms or variations that would warrant a 5.

4 / 5

Distinctiveness Conflict Risk

The ECC-native framing carves a clear niche, but the broad setup/audit scope carries minor overlap risk with general setup or review skills, keeping it just below a 5.

4 / 5

Total

18

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
affaan-m/ECC
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.