CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

88%

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 1-5

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

An exemplary instruction-only skill: lean, fully concrete, with copy-paste commands, exact schemas, and a clear resume sequence. Its one real gap is the missing verification loop around the destructive `mc mirror --overwrite` push, which the skill's own gotcha about losing unpushed work makes conspicuous.

Suggestions

Add a validation step after the `mc mirror` push (e.g. re-list the remote directory or check the command's exit output) and instruct to retry on failure, since the skill's own gotcha warns that session resets can lose unpushed work.

Clarify what to do if `task-history.json` has no entry for the task-id (e.g. fall back to listing the shared tasks directory) so the resume flow handles the missing-history edge case.

Specify the timezone convention for `HH:MM` and `YYYY-MM-DD` timestamps so progress entries sort deterministically across machines.

DimensionReasoningScore

Conciseness

Every line carries non-obvious, environment-specific information (exact paths, the LRU-10 rule, the mc mirror command, the log entry template); there is no explanation of concepts Claude already knows and no padding. This matches the lean anchor — nothing could be trimmed without losing information.

5 / 5

Actionability

Fully executable throughout: exact file paths, a copy-paste `mc mirror ... --overwrite --exclude "spec.md"` command, a complete JSON example for task-history.json, an exact markdown template for log entries, and a concrete numbered resume procedure. Nothing is pseudocode or hand-wavy.

5 / 5

Workflow Clarity

The resume flow is a clear numbered sequence and the LRU/status rules are explicit, but the `mc mirror --overwrite` push is a destructive batch operation with no validation checkpoint that the push succeeded — even though the gotcha itself warns "session resets can lose unpushed work". Per the rubric guideline, a workflow with a destructive/batch step and no verification caps at 3; it is not 2 because the sequences themselves are complete and unambiguous.

3 / 5

Progressive Disclosure

This is a compact single-file skill (~65 lines) with no bundle files present (no references/, scripts/, or assets/ directories exist) and no external references needed; the content is appropriately inlined and well-organized under clear Gotchas / Progress Log / Task History / Resume Flow headers. Per the rubric's simple-skill guidance, well-organized sections with no need for external references score 5.

5 / 5

Total

18

/

20

Passed

Description

83%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.

A strong description with explicit, well-structured "Use when..." triggers covering both the doing-work and resuming-work cases, plus a concrete "what" clause naming the file formats involved. Its only weaknesses are slightly generic leading trigger terms and missing synonyms.

Suggestions

Add one or two natural synonyms for the trigger terms, e.g. "checkpoint my work", "status update", or "pick up task where it left off", to broaden natural-language matching.

Sharpen the leading trigger from "executing a task" to something narrower like "logging or syncing task progress during multi-step agent tasks" to reduce overlap with generic task-management skills.

Mention the push/sync behavior ("pushing progress logs to shared task storage") in the what-clause so the persistence capability is discoverable from the description alone.

DimensionReasoningScore

Specificity

Names several specific actions and artifacts — "progress logging, plan updates", "resuming a task after session reset", "managing task history", "task-history.json" — but omits concrete capabilities like pushing/syncing task directories and the LRU history rules, so it falls just short of the comprehensive anchor.

4 / 5

Completeness

It explicitly answers "when" with three concrete "Use when..." triggers (executing a task, resuming after session reset, managing task history) and "what" with "Covers progress log format, task-history.json, and resume flow", matching the top anchor. Not below 4 because both what and when are explicit and concrete.

5 / 5

Trigger Term Quality

Natural phrases like "progress logging", "resume a task after session reset", and "task history" match what a user would actually say, but common variations such as "checkpoint", "status update", or "pick up where I left off" are missing.

4 / 5

Distinctiveness Conflict Risk

The task-progress/resume-flow niche with artifacts like task-history.json is mostly distinct, but the opening trigger "executing a task (progress logging, plan updates)" is broad enough to overlap with general planning or task-management skills. Not 5 because of that residual overlap; not 3 because the resume and history triggers are clearly unique.

4 / 5

Total

17

/

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

agentscope-ai/AgentTeams

Path

manager/agent/openhuman-worker-agent/skills/task-progress/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.