CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cancel

Cancel stuck or orphaned executions

Quality

80%

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

100%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 instruction-only skill: lean, fully actionable with exact tool names, parameters, CLI fallbacks, and expected outputs, with explicit outcome validation and error-recovery loops for every branch including the batch case. There is no meaningful padding or structural waste.

DimensionReasoningScore

Conciseness

The body is dense and lean with zero padding: every line carries operational knowledge Claude would not have (tool names, the deferred-schema guard behavior, per-error semantics like "`cancellation_requested` means the live worker was asked to stop and will record the cancellation itself"). Nothing explains concepts Claude already knows, so it fits the 'every token earns its place' anchor rather than the 'minor trimming' anchor at 4.

5 / 5

Actionability

Fully executable guidance for an instruction-only skill: exact tool calls with parameters ("call `ouroboros_cancel_execution` with `execution_id` and, if the user gave one, `reason`"), copy-paste CLI commands ("`ouroboros cancel execution --list`", "`--reason \"<text>\"`"), and exact discovery strings ("`+ouroboros project status`"). All common branches (no ID, ID given, --all, no MCP server) are covered, matching anchor 5; per the rubric's scoring notes, the absence of literal code blocks is not penalized for MCP-tool skills when guidance is this concrete.

5 / 5

Workflow Clarity

Clear branching sequence by input form with explicit validation checkpoints ("`new_status` `cancelled` means it is cancelled"), feedback loops for error recovery ("'Failed to persist cancellation' is retriable; retry once", "skip it with a warning" for terminal-state errors during batch cancel), and a verification step ("suggest `ooo status` to confirm"). The destructive/batch cap at 3 does not apply because validation and error-recovery steps are present throughout.

5 / 5

Progressive Disclosure

The body is roughly 40 lines, needs no external reference files, and is cleanly organized into a usage block, an Instructions section with subsections, a Fallback section, and a footer convention. Per the judging guideline, a skill under 50 lines with no need for external references scores 5 on well-organized sections alone; no bundle files exist to verify and none are referenced.

5 / 5

Total

20

/

20

Passed

Description

53%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 concise and specific about its core action, but it undersells the skill's actual capabilities and omits any 'Use when...' trigger guidance. The rich synonyms (kill, abort) exist only as frontmatter aliases rather than in the description text itself.

Suggestions

Add an explicit trigger clause, e.g. "Use when an execution hangs, is orphaned, or a background job needs stopping."

Fold natural synonyms users actually say (kill, abort, stop, terminate) into the description text instead of relying only on frontmatter aliases.

Mention listing active executions and background jobs so the description reflects the skill's full capability set.

DimensionReasoningScore

Specificity

Names one concrete action ("Cancel") on a specific target class ("stuck or orphaned executions"), matching the anchor for 1-2 concrete actions without comprehensive coverage. It does not mention listing active executions, background jobs, or bulk cancel, so it is not a 4; the targets are specific rather than generic, so it is not a 2.

3 / 5

Completeness

The "what" is clear ("Cancel stuck or orphaned executions") but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 4 because the "when" is entirely absent rather than merely less explicit.

3 / 5

Trigger Term Quality

"Cancel", "stuck", and "orphaned" are natural user terms, but common synonyms users say ("kill", "abort", "stop", "terminate") appear only as frontmatter aliases, not in the description, and there is no mention of background jobs. Some relevant keywords with missing variations fits anchor 3 better than 4.

3 / 5

Distinctiveness Conflict Risk

"stuck or orphaned executions" carves a fairly distinct niche in an orchestration context, with only minor overlap risk against generic process-kill or shell skills. It falls short of 5 because nothing in the description distinguishes it from a generic 'cancel my stuck job' request that a shell-based skill might equally claim.

4 / 5

Total

13

/

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.

Validation — 15 / 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

Path

skills/cancel/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.