cc-skill-strategic-compact

Prepare a verified checkpoint before condensing an agent conversation at a phase boundary. Use during long tasks when context is repetitive; preserves constraints, evidence, decisions and the next action.

Quality

71%

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 ./skills/cc-skill-strategic-compact/SKILL.md

Quality

Content

75%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.

A dense, well-structured instruction skill: a sequenced procedure with validation checkpoints, a copy-paste checkpoint template, and honest limitations. The main gaps are a changelog-style paragraph that costs tokens, a script reference that cannot be verified against the bundle, and missing exact commands for the reconciliation step.

Suggestions

Ship suggest-compact.sh in a scripts/ directory (or inline its trivial logic) so the referenced command is actually present in the bundle.

Add the exact reconciliation commands (e.g. git status, git log -1 --format=%H, git diff --stat) to procedure step 2 to make it fully executable.

Move the "Earlier versions incremented a shared user-state counter" migration note into a short 'Migration' or 'Deprecated behavior' subsection so the main procedure stays lean.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence ("A tool-call count is only a reminder; it cannot measure context quality or decide when compaction is safe") with no filler explanations, but the "Earlier versions incremented a shared user-state counter" changelog paragraph is history that could be trimmed, fitting anchor 4 rather than anchor 5's every-token-earns-its-place.	4 / 5
Actionability	A copy-paste checkpoint template, an exact bash invocation with env vars (COMPACT_TOOL_COUNT, COMPACT_THRESHOLD) and a concrete worked example give mostly executable guidance; it falls short of anchor 5 because "Reconcile task state with the filesystem and Git" names no exact commands and the referenced suggest-compact.sh is absent from the bundle.	4 / 5
Workflow Clarity	The six-step procedure is clearly sequenced with explicit validation checkpoints (step 4 checks the next action would not "repeat a merge, send a message twice, lose a constraint"; step 6 requires verifying mutable state on resumption), matching anchor 4; anchor 5 is not reached because there is no fix-and-retry feedback loop around the verification steps.	4 / 5
Progressive Disclosure	Sections are well-organized and appropriately sized for a single-file skill, but the body is just over 50 lines and references a script path (skills/cc-skill-strategic-compact/suggest-compact.sh) that does not exist in the bundle, leaving a minor organization gap at anchor 4.	4 / 5
	Total	16 / 20 Passed

Description

67%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 concise, third-person description that clearly states both what the skill does and when to use it, with a well-scoped niche. Its main weakness is trigger-term coverage: users asking to 'compact' or noting a 'full context window' would not naturally match the current phrasing.

Suggestions

Add natural trigger synonyms to the when-clause, e.g. 'Use when the user asks to compact, summarize, or condense a long conversation, or when the context window fills with repetitive exploration'.

Mention the concrete artifacts the skill produces (checkpoint template with objective, revision, verification results, next action) to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	"Prepare a verified checkpoint" and "condensing an agent conversation at a phase boundary" name several concrete third-person actions, matching anchor 4; it is not anchor 5 because coverage is incomplete (the checkpoint template and state-reconciliation procedure are unstated) and not anchor 3 because more than 1-2 actions are listed.	4 / 5
Completeness	Both what ("Prepare a verified checkpoint before condensing an agent conversation at a phase boundary") and when ("Use during long tasks when context is repetitive") are explicitly present, but the when-clause lacks concrete trigger phrases, so it matches anchor 4 rather than 5.	4 / 5
Trigger Term Quality	"Use during long tasks when context is repetitive" provides a real trigger, but common natural phrases users would say — "compact", "context window", "summarize the conversation" — are missing, fitting anchor 3's 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	"verified checkpoint before condensing an agent conversation at a phase boundary" carves a distinct niche against generic summarization skills with minor overlap risk only, matching anchor 4; anchor 5 would require fully distinct trigger phrasing.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/agentic-awesome-skills
Path: skills/cc-skill-strategic-compact/SKILL.md
Commit: 7b534bc

Reviewed: 5 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.