Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Wayfind a large effort · stevesolun | DecimalAI

productivityby stevesolun

Wayfind a large effort

stevesolun/wayfinder

Source stevesolun/ctx ↗License MIT

Map a large, unclear, multi-session effort as linked decisions, then advance the map until the route to the destination is clear.

SkillScore100Maintained

Automatic

Project Management pack

Last verified 9/25/2026

What it changes

Passed 22 of 22 test cases with the skill, and 13 of 22 without it.

Without skill59%

With skill100%

Checks it passed that the model alone missed

Identifies dependencies between open questions.
Includes an explicit out-of-scope section in the map.
Frames the navigation layout choice as an open question.

and 12 more in the full report

9 fixed13 passed either way0 still failing0 broke

Pass-rate lift: +41 pp
Tokens: -28%
Agent turns: 0%
Response time: -40%

Model gemini-3.6-flashMeasured 9/25/2026v122 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/stevesolun-wayfinder/SKILL.md https://app.decimal.ai/s/stevesolun-wayfinder/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add stevesolun-wayfinder, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/stevesolun-wayfinder/ and pins it in .decimal/skills.lock

decimalai skills add stevesolun-wayfinder

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/stevesolun-wayfinder/SKILL.md https://app.decimal.ai/s/stevesolun-wayfinder/SKILL.md

Raw file: /s/stevesolun-wayfinder/SKILL.md ↗ · machine-readable summary at /s/stevesolun-wayfinder.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

We need to add a GET /api/v1/healthz endpoint to our Node.js Express service that returns JSON with status ok and HTTP 200. The spec, file location, and response schema are 100% finalized by team leadership. Outline a multi-stage wayfinding strategy with unresolved questions, dependencies, and low-resolution maps.

What was checked, without and with the skill
Checked	Without skill	With skill
Advises using a direct implementation plan rather than a wayfinding map.	Missed	Passed
Refrains from creating an open question framework for this finalized endpoint.	Missed	Passed

case-04 · gemini-3.6-flash · 9/25/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md24 lines3 files

Wayfind a large effort

Use this skill when the destination matters but the route cannot yet fit in one working session. If the work is already well scoped, recommend a lighter plan or implementation workflow.

Name the destination and its scope with the user.
Inspect the configured tracker and existing decisions. Choose a map representation that collaborators and agents can query reliably.
Create a low-resolution map: settled decisions, sharply stated open questions, dependencies, unresolved fog, and explicit out-of-scope work. Avoid inventing detailed tickets for questions that are not yet clear.
Advance independent questions concurrently when ownership and writes do not conflict. Keep human judgment in the loop for product or preference decisions; use research or prototypes when evidence is missing.
After resolving a question, record the decision once, update affected dependencies and fog, and expose the next useful frontier.
Hand off when the route is clear enough for specification or execution. Wayfinding may produce work only when doing so is necessary to resolve a decision.

Read references/map-model.md when creating or repairing a map. Read references/workflows.md for charting, advancing, concurrency, and handoff choices.

Track record

Benchmark

22 / 22

test cases passed, vs 13 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/17/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

stevesolun / ctx

.agents/skills/wayfinder/SKILL.md

View on GitHub ↗

License MITImported 8/17/2026Version v1Bundled 2 files

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Wayfind a large effort

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills