status

Show current goal-plan status at a glance - phases, progress, checklist, verification, and risks.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/status/SKILL.md

Quality

Content

92%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 instruction-only skill: well-sectioned, concrete output template, explicit ambiguity and missing-file handling, and a clear brevity principle. The only meaningful gap is the truncated fallback command and a couple of under-specified extraction pointers (e.g., where verification evidence lives).

Suggestions

Complete the fallback command instead of truncating it with "..." so it is copy-paste runnable, or replace it with the exact argument(s) to pass to create-goal-scratchpad.mjs.

Specify where each "What to Show" item comes from in the plan file (e.g., which table/heading holds verification evidence and error attempts) to remove ambiguity during extraction.

Optionally state the expected docs/plans filename convention (e.g., YYYY-MM-DD-goal.md) so the "most relevant recent" selection rule is deterministic.

Dimension	Reasoning	Score
Conciseness	The body is ~50 lean lines with no padding and no explanation of concepts Claude already knows; every section (What to Show, Status Icons, Output Format, fallback, brevity note) earns its place. Not level 4 because there are no meaningful instances of over-explanation to trim.	5 / 5
Actionability	Concrete guidance throughout: an exact output-format template, a status-icon mapping table, a fallback message, and a specific script path. Not level 5 because the fallback command "node .agents/skills/autogoal/scripts/create-goal-scratchpad.mjs ..." is truncated with "..." and is not copy-paste executable, and "latest verification evidence" gives no pointer to where it lives in the plan file.	4 / 5
Workflow Clarity	This is a simple, non-destructive single-task skill and the single action is unambiguous: locate the active plan (with an explicit disambiguation checkpoint — "if ambiguous, list the likely files and ask" — and a no-files fallback), then render the defined output format. Not level 4 because the sequence, checkpoints, and error-recovery branches are all explicitly present.	5 / 5
Progressive Disclosure	The skill is a single well-organized file with clear section headers and no need for external references; no bundle files (references/, scripts/, assets/) exist, so nothing is inappropriately inlined or buried. Per the simple-skill scoring note, well-organized sections alone warrant a 5 here.	5 / 5
	Total	19 / 20 Passed

Description

66%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 states a clear, concrete capability with a well-enumerated list of what the status view includes, but it lacks any explicit trigger guidance for when the skill should be used. Adding a "Use when..." clause and a few natural user phrases would substantially improve it.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks for goal-plan status, plan progress, or 'where am I' in the current work."

Include natural user variations and file locations (e.g., "docs/plans/*.md") to improve trigger-term coverage and distinctiveness.

Distinguish the skill from generic status checks by naming the artifact explicitly ("goal-plan scratchpad in docs/plans") rather than only "goal-plan".

Dimension	Reasoning	Score
Specificity	"Show current goal-plan status at a glance - phases, progress, checklist, verification, and risks" names a concrete domain action (show status) and enumerates several specific components (phases, progress, checklist, verification, risks). It is not level 5 because it describes one display action with its contents rather than multiple comprehensive concrete actions, and not level 3 because several specific capabilities are explicitly listed.	4 / 5
Completeness	The "what" is clear (shows goal-plan status with phases, progress, checklist, verification, risks), but there is no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines. It is not level 4 because the "when" is entirely absent rather than merely implicit.	3 / 5
Trigger Term Quality	Natural terms a user would say are present: "status", "goal-plan status", "progress", "checklist", "phases". It is not level 5 because common variations users might actually say (e.g., "where am I", "plan summary", "current state") and file extensions (docs/plans/*.md) are missing; not level 3 because keyword coverage is good, not just partial.	4 / 5
Distinctiveness Conflict Risk	The niche is fairly clear — goal-plan status for docs/plans files — with minor overlap risk against generic "status" or "progress report" skills. Not level 5 because "status" alone is a broad term many skills could claim; not level 3 because the goal-plan framing makes it mostly distinct.	4 / 5
	Total	15 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/status/SKILL.md
Commit: babb3c2

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.