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

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

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 lean, fully actionable skill body — concrete paths, templates, and commands with zero padding. The one real gap is validation: the batch mc mirror push and the LRU history eviction proceed without any verification checkpoints.

Suggestions

Add a verification step after the mc mirror push (e.g. check the command's exit status or list the remote prefix to confirm the latest progress file landed) before considering an update durable.

Add a checkpoint to the LRU eviction rule (e.g. confirm {task-id}.json exists in history-tasks/ before removing the entry from recent_tasks) so the overflow move cannot silently lose history.

In the resume flow, add a fallback checkpoint when task-history.json or the task_dir is missing (e.g. how to locate the task directory from ~/shared/tasks/) instead of only the single history-tasks lookup.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: no concept explanations, no padding, and every line (paths, format template, command, JSON example, rules) is operational — matching 'every token earns its place'. It is not below 5 since nothing explains what Claude already knows.

5 / 5

Actionability

Concrete file paths (~/shared/tasks/{task-id}/progress/YYYY-MM-DD.md), a copy-paste-ready append format, a complete mc mirror command with flags and env var, a full JSON example, and a named sync command (hermes-sync) cover the common cases. Not 4 because there is no pseudocode or vague step anywhere.

5 / 5

Workflow Clarity

The resume flow is a clear 5-step latest-first sequence, but validation checkpoints are absent throughout: the batch/destructive 'mc mirror --overwrite' push has no success verification, and the LRU eviction to history-tasks has no post-move check. Per the rubric's cap, a workflow involving batch operations without validation cannot score above 3; it is not 2 because the sequence itself is coherent and well-defined.

3 / 5

Progressive Disclosure

There are no bundle files and none are needed; the ~65-line body is organized into four tight sections (Gotchas, Progress Log, Task History, Resume Flow) with nothing that belongs in a separate file, fitting the simple-skill exception. Not 4 because organization is clean and navigation is trivial.

5 / 5

Total

18

/

20

Passed

Description

75%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 well-formed description with explicit, specific trigger conditions and a distinct niche. Its main weakness is the passive 'what' clause — it names the artifacts covered but not the concrete actions performed on them.

Suggestions

Rewrite the 'what' with explicit action verbs, e.g. 'Append timestamped progress entries, maintain an LRU task-history.json, and resume tasks from pushed progress logs' instead of 'Covers progress log format, task-history.json, and resume flow'.

Add natural trigger synonyms such as 'continue a task' or 'pick up where you left off' alongside 'resuming a task after session reset'.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "progress logging, plan updates", "resuming a task after session reset", "managing task history", and the concrete artifact "task-history.json" — which matches the 'several specific actions; minor gaps' anchor. Not 5 because the framing 'executing a task' is generic and the capabilities lack action verbs (append, push, update, evict).

4 / 5

Completeness

It has both an explicit 'Use when...' with three concrete trigger conditions and a stated 'what' ("Covers progress log format, task-history.json, and resume flow"), fitting the 'both what and when; when could be more explicit' anchor inverted — here the 'what' is the weaker half. Not 5 because the 'what' is a passive 'covers X' list rather than explicit capability statements.

4 / 5

Trigger Term Quality

Natural phrases users would say are present: "progress logging", "resuming a task", "session reset", "task history", matching the 'good keyword coverage; a few natural terms missing' anchor. Not 5 because synonyms such as "continue a task" or "pick up where I left off" are absent.

4 / 5

Distinctiveness Conflict Risk

Triggers like "resuming a task after session reset", "task-history.json", and "progress log format" carve a clear niche with minor overlap risk against generic task- or plan-management skills. Not 5 because "executing a task" and "plan updates" could collide with broader planning skills.

4 / 5

Total

16

/

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/hermes-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.