CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

apm-5-check-reports

Deliver a Task Report to an APM Manager. Use only when the User manually invokes this skill.

Quality

76%

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 ./templates/skills/apm-5-check-reports/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 lean, manual-invocation instruction skill: precise paths, explicit conditionals and stop conditions, and cleanly delegated detail via clearly signaled external references. The only meaningful gap is that the post-review delivery step is not spelled out.

DimensionReasoningScore

Conciseness

The 14-line body is lean and directive ("read every non-empty `.apm/bus/*/report.md`", "If you are not the Manager, tell the User and stop") with zero explanation of concepts Claude already knows; every sentence is an instruction. This matches 'lean and efficient; assumes Claude's competence; every token earns its place'.

5 / 5

Actionability

Concrete glob paths (`.apm/bus/*/report.md`), explicit agent-ID conditionals, and precise section pointers ("`{SKILL_PATH:apm-communication}` §3.2", "`{GUIDE_PATH:task-review}`") make the guidance mostly executable with minor gaps — matching anchor 4. Not a 5 because the bus-folder matching procedure and review criteria are delegated rather than specified inline.

4 / 5

Workflow Clarity

A clear 3-step sequence with guard clauses ("If you are not the Manager... stop", "If no Task Report is waiting, say so and wait") and an anomaly check ("Tell the User about any content you did not expect") fits 'clear sequence with most checkpoints present'. Not a 5 because the action following step 3's review (how to deliver/summarize results) is left unspecified. The destructive/batch validation cap does not apply since this is a read-only relay skill.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files, and the body is well organized (heading, context paragraph, numbered steps) with its two external references clearly signaled one level deep via path placeholders. Per the rubric's simple-skill guideline, this earns a 5 with just well-organized sections.

5 / 5

Total

18

/

20

Passed

Description

55%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 clearly states what the skill does and is explicit that it fires only on manual invocation, which is appropriate for a disable-model-invocation skill. However, it under-describes the concrete mechanics (reading Workers' report.md files from bus folders) and contains almost no natural trigger vocabulary a user would say.

Suggestions

Expand the what-clause to name the concrete actions, e.g. "Read Workers' report.md files from the APM bus and deliver them as Task Reports to the Manager" — this would raise specificity.

Include the natural phrases a user would say when invoking it (e.g. "task reports", "check reports") so the description is discoverable and readable, even for a manual-invocation skill.

Mention the agent-ID filtering option ("optionally limited to specific Workers by agent ID") to sharpen distinctiveness from sibling APM communication skills.

DimensionReasoningScore

Specificity

"Deliver a Task Report to an APM Manager" names the domain and one concrete action, matching the '1-2 concrete actions, but not comprehensive' anchor. It is not generic enough for a 2, but lacks the several specific actions (reading report.md files, agent-ID filtering) needed for a 4.

3 / 5

Completeness

Both parts are explicit: the what ("Deliver a Task Report to an APM Manager") and the when ("Use only when the User manually invokes this skill"), matching the 'both present, when could be more explicit/specific' anchor. Not a 5 because the what is thin and there are no concrete trigger phrases beyond manual invocation.

4 / 5

Trigger Term Quality

The only keywords are "Task Report" and "APM Manager", which are domain jargon; no natural user phrases like "check reports" or "worker reports" appear. This fits 'one or two generic keywords; missing the natural phrases users say' rather than a 1, since "Task Report" is at least a relevant term.

2 / 5

Distinctiveness Conflict Risk

The manual-invocation-only gate and the manager-report-delivery niche keep conflict risk low, but the phrasing could overlap with sibling APM communication skills, fitting 'mostly distinct; minor overlap risk with closely related skills'. Not a 5 because distinctiveness rests on the APM context rather than distinct trigger phrases.

4 / 5

Total

13

/

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

sdi2200262/agentic-project-management

Path

templates/skills/apm-5-check-reports/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.