CtrlK
BlogDocsLog inGet started
Tessl Logo

oac-approach

Use before any implementation — understands the request, discovers project context, and proposes a concise plan for user approval before writing any code.

70

Quality

85%

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A clearly structured, actionable planning workflow with a strong approval gate and feedback loop. Its one weakness is mild redundancy between the step prose and the Key Principles recap, which inflates the token budget slightly.

Suggestions

Trim the 'Key Principles' section to only principles not already implied by the steps, or fold the unique ones (e.g. YAGNI, Assumptions over questions) into their relevant steps.

Consolidate the clarifying-question guidance so it lives in one step rather than being introduced in Step 1 and revisited in Step 3.

DimensionReasoningScore

Conciseness

Mostly efficient, but the 'Key Principles' section restates points already made in the steps and clarifying-question guidance is split across Steps 1 and 3, so it could be tightened.

2 / 3

Actionability

Gives concrete, copy-paste-ready guidance: named invocations (oac:context-discovery), a filled-in proposal template with explicit fields, and a numeric simple/complex threshold (1–3 vs 4+ files).

3 / 3

Workflow Clarity

A clearly sequenced 6-step process with an explicit HARD-GATE approval checkpoint and an adjust→re-ask feedback loop, satisfying the validation-checkpoint and error-recovery anchors.

3 / 3

Progressive Disclosure

Well-organized into Overview, sequenced steps, Key Principles, and a one-level-deep Related section; no bundle files exist and references are to sibling skills rather than nested files, so the single-file structure is appropriate.

3 / 3

Total

11

/

12

Passed

Description

85%

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 strong, third-person description that names concrete actions and carries an explicit trigger plus the when-to-use condition. Its main weakness is narrow trigger-term coverage, relying almost entirely on the single phrase 'implementation'.

Suggestions

Broaden trigger terms to natural user phrasings such as 'plan before coding', 'review the approach first', or 'before implementing a feature' to improve trigger recall.

Consider naming the key artifact the skill produces (a proposal/approval gate) more directly so the capability is unambiguous at a glance.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'understands the request, discovers project context, and proposes a concise plan for user approval' — each a distinct, specific step rather than a single vague verb.

3 / 3

Completeness

It answers both what (understand, discover, propose plan) and when via the explicit trigger 'Use before any implementation', so it is not capped at 2 by the missing-trigger guideline.

3 / 3

Trigger Term Quality

The only natural trigger is 'before any implementation'; it is relevant but coverage of common phrasings ('plan before coding', 'review the approach first') is thin, matching the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

The pre-implementation approval-gate niche is distinct and its 'before any implementation' trigger is specific enough that it is unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
darrenhinde/OpenAgentsControl
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.