log-session
Skill0 starsChanged 4 months agoMITView on GitHub
Log a surf session or visual spot check locally and update private forecast calibration. Use when the user reports what conditions were actually like.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- thiagofinch/mega-braintheir own version, first seen Oct 8, 2026
- gtrabanco/agentic-workflowtheir own version, first seen Sep 22, 2026
- Faaz17/Agents-and-Skillstheir own version, first seen Sep 8, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- thiagofinch/mega-brain★ 95same name
- gtrabanco/agentic-workflow★ 23same name
- Faaz17/Agents-and-Skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- board-recommendSkill
- scanSkill
- setup-surfSkill
- surfSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 3 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
If it is missing, tell the user to run /setup-surf.
- Very specific: line 17
If its status is none, stop before resolving any region paths.
- Distinctive: line 34
Ask only for fields necessary to avoid a misleading record:
- Distinctive: line 44
Never invent missing forecast values.
- Very specific: line 54
Update data/calibration/<region>.md only when the observation changes a useful private rule.
- Very specific: line 59
Follow method/calibration-promotion.md after updating the private record.
- Distinctive: line 65
update to an existing candidate.
- Very specific: line 77
Do not edit locations/ during session logging.
- Very specific: line 82
Do not write raw sessions under locations/.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Log a session
Record the user's session report as private ground truth.
Load
Read data/active-location.md first.
If it is missing, tell the user to run /setup-surf.
If its status is none, stop before resolving any region paths. Explain that
there is no active destination and offer either:
/setup-surfto activate the next trip; or- logging against a named archived region, but only after the user explicitly identifies that region.
For an active destination, verify that the region slug and every configured session/calibration path are non-empty. Then read:
templates/sessions.csv- the active
data/sessions/<region>.csv - the active
data/sessions/<region>.md - the active
data/calibration/<region>.md
Clarify
Ask only for fields necessary to avoid a misleading record:
- date, public spot name, and approximate time window;
- surfed or visual check;
- observed face height, cleanliness, consistency, wind feel, and verdict;
- forecast numbers only if they were saved in the prior conversation or the user provides them;
- a primary and alternate wind-source value when both were captured;
- what matched and what missed.
Never invent missing forecast values. Leave CSV fields empty.
Write locally
Append:
- One concise prose entry to
data/sessions/<region>.md. - One CSV row per checked spot to
data/sessions/<region>.csv, following the exact template schema.
Update data/calibration/<region>.md only when the observation changes a useful
private rule. Preserve counterexamples and evidence counts.
Evaluate a reusable lesson
Follow method/calibration-promotion.md after updating the private record.
Classify the result as:
- personal-only;
- needs more evidence;
- candidate public lesson; or
- update to an existing candidate.
For a candidate, add or update a stable entry in the private calibration's
Candidate public lessons table. Keep its evidence references private. Draft a
separate anonymized public rule with:
- public spot name and condition bucket;
- generalized model or geometry behaviour;
- observation count and independent-contributor count;
- counterexamples, uncertainty, evidence label, and confidence;
- the target
locations/<country>/<region>/calibration.md.
Do not edit locations/ during session logging. Show the proposed public rule
to the user and ask for explicit approval in a later contribution step.
Privacy
Do not write raw sessions under locations/. If a lesson appears broadly
useful, separately offer the anonymized proposal described above.
Preparing a public contribution requires explicit approval. Repeated sessions from this user still count as one independent contributor.
Finish by summarizing what was logged and which private calibration rule, if any, changed. Also report the candidate lesson status without implying that it has already been published.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.