Name: context-surfing
Rating: 66.4 (1 reviews)
Author: pskoett

context-surfing

Monitors context window health during large, long-running, multi-session, or explicitly context-sensitive work. Uses bounded external anchors, one cold-context review when self-recovery is uncertain, and a clean handoff on real drift. Do not auto-activate merely because a medium task has an intent frame and plan.

Quality

78%

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 ./agent-plugin/skills/context-surfing/SKILL.md

The canonical home for this skill is context-surfing in pskoett/pskoett-ai-skills

Quality

Content

73%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 a well-sequenced, actionable process skill with strong workflow clarity and a real bundled hook script. Its main weakness is conciseness: an extended metaphor and repeated protocol restatements inflate the token budget without adding operational value.

Suggestions

Collapse the "Mental Model" surfing metaphor to one or two lines, or move it to a reference file; the wave imagery is reiterated throughout and competes with operational tokens.

De-duplicate the pre-commit anchor check: define it once in "The Monitoring Paradox" and have "Riding the Wave" and "Recovery Protocol" reference it rather than restate it.

Split the full handoff-file markdown template and the drift-signal catalog into a references/ file, keeping SKILL.md as an overview that links one level deep.

Dimension	Reasoning	Score
Conciseness	Operational content is genuinely useful, but the extended surfing metaphor ("paddling in", "the shoulder", "the close-out") and repeated restatements of the pre-commit anchor check across three sections add noticeable padding that could be tightened.	3 / 5
Actionability	Provides copy-paste-ready artifacts: a full handoff-file markdown template, a real SessionStart hook JSON config, and a complete executable scripts/handoff-checker.sh, plus real CLI commands ("entire status", "entire explain --session <id>"). Minor gaps remain where guidance stays abstract ("execute with commitment").	4 / 5
Workflow Clarity	Activation, Recovery Protocol, and Exit Protocol are explicitly numbered with validation checkpoints and feedback loops (re-anchor → resolve → resume / escalate → exit), and the handoff template functions as a checklist; this matches the clear-sequence-with-feedback-loops anchor.	5 / 5
Progressive Disclosure	Section structure is well-organized with clear headers and logical navigation, the one bundle file (scripts/handoff-checker.sh) is appropriately externalized, and external-skill references are clearly signaled; the gap is the large monolithic SKILL.md that could split detailed reference material (drift catalog, handoff template) into separate files.	4 / 5
	Total	16 / 20 Passed

Description

83%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 strong: it answers both what and when with concrete trigger phrases and explicit anti-activation guidance, and carves a distinct niche. It is held back only by mildly abstract phrasing ("bounded external anchors") rather than truly comprehensive, plain-language capability listing.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Monitors context window health", "Uses bounded external anchors", "one cold-context review", "a clean handoff on real drift" — but "bounded external anchors" is somewhat abstract, keeping it just below comprehensive coverage.	4 / 5
Completeness	Clearly states what it does (monitor, anchors, cold-context review, handoff) and gives explicit when-triggers ("during large, long-running, multi-session, or explicitly context-sensitive work") plus negative guidance ("Do not auto-activate merely because a medium task has an intent frame and plan").	5 / 5
Trigger Term Quality	Natural domain terms like "context window health", "long-running", "multi-session", "drift", and "handoff" are present, but jargon such as "bounded external anchors" and "cold-context review" plus absent synonyms keep it from full coverage.	4 / 5
Distinctiveness Conflict Risk	The niche (context-quality drift vs scope drift) is fairly distinct from sibling skills, but the broad phrase "explicitly context-sensitive work" leaves minor overlap risk with closely related monitoring skills.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: pskoett/pskoett-ai-skills
Path: agent-plugin/skills/context-surfing/SKILL.md
Commit: 8a71d70

Reviewed: 6 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.