context-manager

Context management skill providing discovery, fetching, harvesting, extraction, compression, organization, cleanup, and guided workflows for project context

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/context-manager/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable, giving concrete executable router.sh commands with multiple examples per operation, but it is verbose due to restating the same eight operations several times and keeps all detail inline rather than splitting it into the referenced bundle files. Destructive workflows lack explicit validation checkpoints, and the listed supporting files do not actually exist.

Suggestions

Collapse the redundant coverage: keep executable Quick Start commands and a compact Operations Reference, and remove the restated Success Criteria / Tips sections or merge them into the reference.

Add explicit validation checkpoints to destructive/batch workflows (e.g., cleanup, compress): show a dry-run listing, a confirmation gate, and a verify-after/recover-from-backup step inside the sequence.

Either create the referenced bundle files (CONTEXT_SKILL_QUICK_START.md, context-manager.md, navigation.md) and link to them inline, or remove the File Structure listing so progressive disclosure matches the actual bundle.

Dimension	Reasoning	Score
Conciseness	The ~550-line body restates the same eight operations across Quick Start, Operations Reference, Common Workflows, Success Criteria, and Tips, plus generic 'Output' bullets like 'Suggestions for next steps'; it is mostly actionable but heavily redundant and could be tightened considerably.	2 / 3
Actionability	Each operation ships concrete, executable commands (e.g., 'bash .opencode/skills/context-manager/router.sh discover authentication') with multiple copy-paste-ready examples and explicit syntax blocks.	3 / 3
Workflow Clarity	Common Workflows provides clear sequences, but destructive/batch operations (cleanup, compress) lack embedded validate→fix→retry checkpoints; 'Safe Operations' is stated as an abstract principle rather than woven into the workflows, so workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	No bundle files exist in references/, scripts/, or assets/, yet the File Structure section lists router.sh and several .md files that are neither present nor linked inline; the per-operation detail that belongs in a separate reference file is inlined in SKILL.md, so structure exists but content is not appropriately split.	2 / 3
	Total	9 / 12 Passed

Description

60%

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 strong on specificity by listing eight concrete operations, but lacks any explicit 'when to use' trigger guidance and leans on skill-internal jargon rather than natural user phrasing, which caps completeness and trigger-term quality. It occupies a recognizable niche but is generic enough to risk overlap with adjacent file/document skills.

Suggestions

Add an explicit 'Use when…' clause naming natural user triggers (e.g., 'Use when organizing or finding project context files, fetching external docs, or cleaning up stale context').

Replace skill-internal operation names ('harvest', 'fetch', 'extract') in the description with phrasings a user would actually say, and include common variations (e.g., 'find context', 'organize context files', 'pull in library docs').

Sharpen the niche by naming the target artifact (e.g., '.opencode/context/' files) so it is less likely to collide with generic file-management skills.

Dimension	Reasoning	Score
Specificity	The description enumerates eight concrete operations ('discovery, fetching, harvesting, extraction, compression, organization, cleanup, and guided workflows') on a named domain ('project context'), matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	It states what the skill does (the eight operations) but provides no 'Use when…' clause or equivalent explicit trigger guidance, so the 'when' is only implied and completeness is capped at 2 per the rubric.	2 / 3
Trigger Term Quality	It uses the skill's internal operation names ('harvesting', 'fetching', 'extraction') rather than phrasings a user would naturally say; only 'context', 'organization', and 'cleanup' read as natural trigger terms, so common variations are missing.	2 / 3
Distinctiveness Conflict Risk	'Context management' and 'project context' are broad and could overlap with file- or document-management skills; the operations give it a niche but the triggers are not distinct enough to rule out conflicts.	2 / 3
	Total	9 / 12 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
skill_md_line_count	SKILL.md is long (569 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: darrenhinde/OpenAgentsControl
Path: .opencode/skills/context-manager/SKILL.md
Commit: 37ca233

Reviewed: 3 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.