CtrlK
BlogDocsLog inGet started
Tessl Logo

task-progress

Use when executing a task (progress logging, plan updates), when resuming a task after session reset, or when managing task history. Covers progress log format, task-history.json, and resume flow.

71

Quality

86%

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

87%Weight 40%Scale 1-3

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

Concise and highly actionable with concrete commands and templates, plus a well-organized self-contained structure. The gap is workflow clarity: clear steps but no validation checkpoints or error recovery around the overwrite/sync operations.

Suggestions

Add explicit validation checkpoints, e.g., confirm the `mc mirror` push succeeded before proceeding, and verify `spec.md`/`plan.md` exist during resume before reading them.

Include an error-recovery note for the resume flow (e.g., what to do if `task-history.json` is missing, empty, or `hermes-sync` fails).

Note the destructive nature of `mc mirror --overwrite` and add a guard (e.g., confirm the task-id directory is correct before mirroring).

DimensionReasoningScore

Conciseness

Lean and efficient: gives paths, format templates, a command, and a JSON schema directly without explaining what progress logging or LRU caches are; assumes Claude's competence throughout.

3 / 3

Actionability

Provides concrete file paths, a copy-paste `mc mirror` push command with flags, an exact progress-log template, and a JSON schema — executable rather than descriptive.

3 / 3

Workflow Clarity

The resume flow is a clear 5-step sequence, but there are no validation checkpoints or error-recovery feedback loops, and the `mc mirror --overwrite` push is a batch/overwrite operation that should trigger the cap at 2.

2 / 3

Progressive Disclosure

A self-contained, well-organized skill (Gotchas, Progress Log, Task History, Resume Flow) with no external references needed, scoring 3 under the simple-skills note for under-50-line-ish content with clear sections.

3 / 3

Total

11

/

12

Passed

Description

85%Weight 40%Scale 1-3

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 clearly states both capability and explicit 'Use when' triggers around a distinct task-progress niche. The only weak spot is trigger phrasing, which leans on internal artifact names over natural user language.

Suggestions

Add natural-language trigger variants a user might actually say (e.g., 'continue where I left off', 'pick up my task after a reset') alongside the technical term 'task-history.json'.

Soften jargon in the trigger clause by leading with user-facing phrasing ('when continuing or resuming a task') before naming the internal artifact.

DimensionReasoningScore

Specificity

Names multiple concrete actions ("progress logging, plan updates", "resuming a task after session reset", "managing task history") tied to named artifacts (task-history.json, resume flow), matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what ("Covers progress log format, task-history.json, and resume flow") and when ("Use when executing a task... when resuming... or when managing task history") with an explicit 'Use when' clause.

3 / 3

Trigger Term Quality

Includes relevant triggers ("resuming a task", "task history", "progress logging") but also leans on technical jargon ("task-history.json", "session reset") and misses common natural phrasings like 'continue where I left off'.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (task progress/resume/history within the hermes task framework) with distinct triggers unlikely to fire for unrelated skills; the broad 'executing a task' opener is narrowed by its parenthetical.

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
agentscope-ai/AgentTeams
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.