CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

apm-7-handoff-worker

Perform a Handoff with an APM Worker. Use only when the User manually invokes this skill.

Quality

83%

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

96%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 tight, fully actionable handoff procedure: exact file paths, ready-to-use templates for both artifacts, a mandated state check before writing, and a user-approval feedback loop that gates completion. It respects the reader's competence with no padding. The only structural headroom is whether the §5 format templates belong in a separate reference file.

DimensionReasoningScore

Conciseness

The body is lean throughout: no concept explanations, every sentence instructs ('Read task.md and report.md in your bus folder', 'Write the Handoff Log per §5.1'), and the one rationale is a single purposeful clause ('Your memory of earlier turns may be out of date, so check the current state'). Matches anchor 5 ('every token earns its place'); not 4 because there is no over-explanation to trim.

5 / 5

Actionability

Concrete, executable guidance throughout: exact paths ('.apm/bus/<agent-slug>/handoff.md', '.apm/memory/handoffs/<agent-slug>/handoff-<NN>.log.md'), two copy-paste-ready markdown templates with frontmatter fields, and three explicit resume branches (mid-Task, mid-batch, between Tasks) covering the common cases. Per the scoring notes, an instruction-only skill needs actionable guidance rather than code; not 4 because there are no material gaps.

5 / 5

Workflow Clarity

Sections 1-4 give a clear sequence (check state → write log → write prompt → user review) with explicit checkpoints: §1 mandates verifying current state before writing either file, and §4 is a literal feedback loop ('Apply their corrections and ask again. After they approve...'). Not a destructive or batch operation so no cap applies; not 4 because validation is explicit rather than implied.

5 / 5

Progressive Disclosure

A well-sectioned single-file procedure (numbered sections, §5 format templates) with one clearly signaled external cross-reference ('{SKILL_PATH:apm-3-initiate-worker} §1.2') and no bundle files. Fits anchor 4 ('Good structure; most content is appropriately placed; minor organization gaps'); not 5 because the ~77-line body exceeds the rubric's under-50-line simple-skill threshold and inlines two full templates that could arguably be split into a reference file.

4 / 5

Total

19

/

20

Passed

Description

61%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 claims a clear niche and an explicit manual-invocation trigger, giving it strong distinctiveness and solid completeness, but the capability statement is thin — 'Perform a Handoff' names the operation without any concrete actions — and natural trigger terms beyond 'Handoff' are missing. It is functional for a manually invoked skill yet undersells what the skill actually does.

Suggestions

Name the concrete actions in the description, e.g. 'Write a Handoff Log and a Handoff Prompt so a new conversation of the same Worker can resume where this one stopped.' (specificity)

Add natural trigger phrases a user would actually say, such as 'handoff', 'continue in a new chat', or 'pass the work to a fresh conversation'. (trigger_term_quality)

State what the handoff produces (the two files and their locations) so the 'what' half is as explicit as the 'when' half. (completeness)

DimensionReasoningScore

Specificity

The description names the domain ('Handoff with an APM Worker') but the only action is the generic 'Perform a Handoff' — no concrete sub-actions (e.g., writing a Handoff Log or Handoff Prompt) are stated. This matches anchor 2 ('Names the domain but actions are minimal or generic', like 'Processes PDF files'); not 3 because there are not 1-2 concrete actions beyond the single generic one.

2 / 5

Completeness

Both parts are explicit: what ('Perform a Handoff with an APM Worker') and when ('Use only when the User manually invokes this skill'). Anchor 4 fits because the when is present but the what is thin — it never says what the handoff produces; not 5 because there are no concrete trigger phrases, and not 3 because an explicit 'Use when...' clause is present so the completeness cap does not apply.

4 / 5

Trigger Term Quality

'Handoff' and 'APM Worker' are relevant domain keywords a user of this system would naturally say, but there are no synonyms or variations such as 'context handoff', 'continue in a new chat', or 'pass off work'. Fits anchor 3 ('Some relevant keywords but missing common variations or synonyms'); not 4 because coverage beyond 'Handoff' is absent.

3 / 5

Distinctiveness Conflict Risk

'Handoff with an APM Worker' carves a clear niche within the APM system, and 'Use only when the User manually invokes this skill' eliminates accidental triggering by other skills. Matches anchor 5 ('Clear niche with distinct triggers; minimal conflict risk'); not 4 because the manual-only restriction leaves no meaningful overlap risk.

5 / 5

Total

14

/

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-7-handoff-worker/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.