CtrlK
BlogDocsLog inGet started
Tessl Logo

cancel

Cancel stuck or orphaned executions

50

Quality

55%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/cancel/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 content is actionable and well-structured with concrete commands and a helpful example, but it stops short of enforcing validation checkpoints for a destructive/batch operation and carries some redundant prose. Adding an explicit verify step and trimming the mode restatement would raise the weakest dimensions.

Suggestions

Insert an explicit validation checkpoint before cancellation (confirm the session is in running/paused status) and an enforced verify-after step (run `ooo status` and report the resulting state) to satisfy the destructive/batch workflow cap.

Remove the restatement of the three modes in "How It Works" or fold it into the Instructions section to reduce redundancy.

Add brief guidance on where to obtain the execution_id (e.g., from `ooo status` or the interactive listing) to close the actionability gap.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete commands and a useful transcript, but the "How It Works" prose restates the three modes already given in Instructions and the example transcript adds length, so it could be tightened.

3 / 5

Actionability

Executable CLI commands are provided for all three modes plus a --reason flag and a worked example transcript, leaving only minor gaps such as where to obtain the execution_id.

4 / 5

Workflow Clarity

A clear 4-step sequenced workflow with mode branching is present, but this destructive/batch operation lacks an explicit pre-cancel validation checkpoint and an enforced verify-after step, so per the rubric cap workflow_clarity cannot exceed 3.

3 / 5

Progressive Disclosure

No bundle files exist and none are needed; the ~109-line body is well-organized with clear section headers covering usage, modes, instructions, state transitions, and fallback, with only minor organization gaps.

4 / 5

Total

14

/

20

Passed

Description

48%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 is clear and reasonably distinct but thin: it states a single action with no explicit use-when guidance and limited keyword coverage. Adding a "Use when..." clause and a few more natural trigger phrases would lift the completeness and trigger-term scores.

Suggestions

Add an explicit "Use when..." clause naming trigger situations, e.g. "Use when an execution is hung, unresponsive, or the user asks to kill/abort a session."

Expand the action vocabulary beyond a single verb to cover the three modes (by ID, --all, interactive) so specificity moves above 2.

Include more natural user phrasings and file/id formats (e.g. "stop a run", "kill the loop", session IDs like sess-*) to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

"Cancel stuck or orphaned executions" names the domain (executions) but offers only a single generic verb with no enumerated actions or modes, matching the anchor for naming a domain with minimal actions.

2 / 5

Completeness

A clear "what" (cancel stuck/orphaned executions) is present, but there is no explicit "Use when..." trigger clause, so per the rubric guideline completeness is capped at 3 with only weakly implied "when".

3 / 5

Trigger Term Quality

"cancel" plus aliases "kill, abort" and the natural phrases "stuck or orphaned" give relevant keywords, but coverage of common user phrasings is incomplete, sitting between the 3 and 4 anchors.

3 / 5

Distinctiveness Conflict Risk

The execution-lifecycle niche is clear and distinct with specific triggers, carrying only minor overlap risk with general stop/status skills.

4 / 5

Total

12

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
Q00/ouroboros
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.