diff --git a/.factory-plugin/marketplace.json b/.factory-plugin/marketplace.json index 4282159..54a2662 100644 --- a/.factory-plugin/marketplace.json +++ b/.factory-plugin/marketplace.json @@ -53,6 +53,12 @@ "description": "Pull request lifecycle skills: create PRs with consistent conventions and follow up on them until merge-ready", "source": "./plugins/code-review", "category": "productivity" + }, + { + "name": "show-me-your-work", + "description": "Auditable TSV decision trail for long-running or unattended agent work, with an end-of-run audit", + "source": "./plugins/show-me-your-work", + "category": "quality" } ] } diff --git a/README.md b/README.md index 9793470..1625181 100644 --- a/README.md +++ b/README.md @@ -96,6 +96,14 @@ Skills for continuous learning and improvement. Autonomous experiment loop for optimization research. Try an idea, measure it, keep what works, discard what doesn't, repeat. Works standalone or as a mission worker. +### show-me-your-work + +Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision. + +**Skills:** + +- `show-me-your-work` - Append-only TSV decision log with evidence pointers and an end-of-run audit + ## Plugin Structure Each plugin follows the Factory plugin format: diff --git a/plugins/show-me-your-work/.factory-plugin/plugin.json b/plugins/show-me-your-work/.factory-plugin/plugin.json new file mode 100644 index 0000000..ca03322 --- /dev/null +++ b/plugins/show-me-your-work/.factory-plugin/plugin.json @@ -0,0 +1,8 @@ +{ + "name": "show-me-your-work", + "description": "Auditable TSV decision trail for long-running or unattended agent work, with an end-of-run audit", + "author": { + "name": "yifu zuo", + "email": "yzuo.2019@gmail.com" + } +} diff --git a/plugins/show-me-your-work/README.md b/plugins/show-me-your-work/README.md new file mode 100644 index 0000000..c0aba8a --- /dev/null +++ b/plugins/show-me-your-work/README.md @@ -0,0 +1,11 @@ +# show-me-your-work + +Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision. + +**Skills:** + +- `show-me-your-work` - Append-only TSV decision log (what, why, evidence, result) with an end-of-run audit and optional cross-model review + +Ships `references/decision-log-template.tsv` and a `scripts/log.sh` helper that appends well-formed, spreadsheet-safe rows. + +Adapted from the pstack skills by Lauren Tan ([cursor/plugins](https://github.com/cursor/plugins), MIT License), with Cursor-specific tooling removed and Droid conventions applied. diff --git a/plugins/show-me-your-work/skills/show-me-your-work/SKILL.md b/plugins/show-me-your-work/skills/show-me-your-work/SKILL.md new file mode 100644 index 0000000..31cf0ec --- /dev/null +++ b/plugins/show-me-your-work/skills/show-me-your-work/SKILL.md @@ -0,0 +1,81 @@ +--- +name: show-me-your-work +description: "Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for autonomous or multi-phase runs, or work a human reviews after stepping away." +--- + +# Show me your work + +Keep one canonical log. + +## The format + +A single TSV file, one row per decision. Cells stay single-line. Evidence is a pointer, not prose. + +Copy `references/decision-log-template.tsv` (the header row) to start a clean log. Columns: + +- **ts.** ISO8601 timestamp. +- **phase.** The phase or workstream. +- **decision.** What was chosen or done, one line. +- **why.** The reason in plain words. If a principle drove it, say it plainly, not as a jargon tag. +- **evidence.** A link or path that proves it: commit SHA, PR number, `file:line`, or an artifact, trace, or screenshot path. Never a paragraph. +- **result.** The outcome or predicate state: `tests green`, `reverted`, `pixel-diff 0`, `INCONCLUSIVE`, `open`. + +An example, plain-spoken so a reviewer reads it at a glance. + +```tsv +ts phase decision why evidence result +2026-05-24T09:02:00Z frame counted the work first, about 100 components and roughly 75 hours wanted to know the size before starting a long run commit 3a9f1c2 found 5 things to sort out before starting +2026-05-24T09:40:00Z harness took screenshots of the old version before changing anything so we can compare old against new and catch any visual change scripts/snapshot.sh, baseline/ saved 120 reference screenshots +2026-05-24T11:15:00Z widget moved the widget styles over without changing how it looks keep the change small and the result identical commit 7c21e0a, pixel-diff 0 looks identical, tests pass +2026-05-24T12:30:00Z widget threw out a helper's work because its screenshots were blank checked the real files instead of trusting its summary worktree reset reverted, tightened the instructions for next time +``` + +## Logging a row + +Write each entry the way you'd tell a teammate what you did. Plain words, concrete actions, no AI speak or abstract jargon. + +Use the helper `scripts/log.sh `. It stamps `ts`, writes the header on first use, strips stray tabs/newlines, and prefixes any cell starting with `=`, `+`, `-`, or `@` with a single quote. A bare `printf` appending a row works too, but mind those same bytes if cells come from generated or user-supplied text. + +Log decision points and checkpoints, not every action: a fork chosen, a unit completed with its verification result, a pivot or revert with its trigger, a blocker surfaced, a gate fixed. For loop runs, one row per iteration. Skip the trivial and self-evident. + +A run is one agent conversation, including its later turns and any summary of it. A pickup, a replacement agent, or a new chat starts a new run. When a run adds to a log that already has rows, its first row has phase `start`, and so does its first row after another run's `start` row. So a run that comes back to a log in a later turn first reads the log's last rows to see whether another run wrote since. A `start` row names the `ts` range of the rows before it that this run did not write, and its evidence names this run, such as its agent id. Use phase `start` for nothing else. + +## Where it lives + +By default the log is a working artifact, not committed. Keep it at `decisions.tsv` in the work dir, or `.audit/.tsv` when several efforts run at once, and leave it out of git. + +Commit it only when the work is ambitious enough that a reviewer needs the trail to trust the result. + +## Rules + +- Append-only. A wrong call gets a new row that supersedes it. Never edit or delete history. +- Prefer evidence produced by committed scripts over hand-made one-offs. + +## Audit the log against the transcript + +At the end of the run, before handing back, check the log told the truth. Read this run's transcript from your harness's transcript directory (the harness docs name the path). Never glob across other projects' transcript directories; that reads unrelated private chats. Walk this run's rows against what actually happened. Each stretch of them begins at one of this run's `start` rows, or at the first row if this run created the log, and ends at the next `start` row of another run: + +- Check that every row maps to a real decision or action. +- Check that each row's evidence resolves and shows what the row claims. +- A fork, pivot, or abandoned approach that shaped the work but isn't logged is a gap. Add it. + +Correct the log, not the story. The audit never edits or removes a row, even an invented one. When a row records neither a real decision nor a real action, or its claim or evidence is wrong, add a row that supersedes it with what actually happened and a pointer that resolves. This audit does not check rows outside this run's stretches. If this run's own work shows one of them is wrong, supersede it like any wrong call. + +## Cross-model review of the trail + +Before handing back, spawn a subagent on a different model family from the one that did the work. Self-review is not a substitute. The subagent reads the audit trail and the run's transcript, then flags what the user should pay attention to. Not a redo of the work, a scan for what's suboptimal or risky: + +- Decisions logged with weak or absent evidence. +- Verification steps skipped or claimed without proof in the transcript. +- Choices that look risky in hindsight (premature, scope-creeping, papering over a symptom). +- Gaps the user would otherwise miss on a casual skim. + +Every reply for a run that produced a trail ends with an "Attention" section. Lead with the reviewer's model on its own line (`reviewed by `), then list each flag pointing to specific rows or moments. "No flags" is a valid value. The model name is not. When only one model family is available, skip this step and say so. + +## Reviewing the trail + +Read top to bottom, follow the evidence pointers, spot-check. GitHub renders a committed TSV as a table. `column -s$'\t' -t decisions.tsv` renders it in a terminal. + +## Composing this skill + +Other skills route their audit trail here instead of inventing one. Reference it by name and let it own the format. Don't restate the columns. diff --git a/plugins/show-me-your-work/skills/show-me-your-work/references/decision-log-template.tsv b/plugins/show-me-your-work/skills/show-me-your-work/references/decision-log-template.tsv new file mode 100644 index 0000000..db22037 --- /dev/null +++ b/plugins/show-me-your-work/skills/show-me-your-work/references/decision-log-template.tsv @@ -0,0 +1 @@ +ts phase decision why evidence result diff --git a/plugins/show-me-your-work/skills/show-me-your-work/scripts/log.sh b/plugins/show-me-your-work/skills/show-me-your-work/scripts/log.sh new file mode 100755 index 0000000..052e53b --- /dev/null +++ b/plugins/show-me-your-work/skills/show-me-your-work/scripts/log.sh @@ -0,0 +1,42 @@ +#!/usr/bin/env bash +# Append a well-formed row to a show-me-your-work decision log (TSV). +# Usage: log.sh +set -euo pipefail + +if [ "$#" -ne 6 ]; then + printf 'usage: log.sh \n' >&2 + exit 1 +fi + +logfile="$1" +shift + +logdir="$(dirname "$logfile")" +if [ -n "$logdir" ] && [ "$logdir" != "." ] && [ ! -d "$logdir" ]; then + mkdir -p "$logdir" +fi + +# Use `>>` here, never `>`. A network mount can fail this test for a log +# that exists. Then the cost is one stray header line, not the rows. +if [ ! -s "$logfile" ]; then + printf 'ts\tphase\tdecision\twhy\tevidence\tresult\n' >> "$logfile" +fi + +ts="$(date -u +%Y-%m-%dT%H:%M:%SZ)" +# Strip tabs/newlines/CR so cells stay on one line, and prefix any cell +# whose first char a spreadsheet would parse as a formula (=, +, -, @) +# with a single quote. The skill expects this log to be read in +# spreadsheets, so attacker-controlled evidence (PR titles, filenames, +# generated text) must not become formula execution when a reviewer +# opens the file. +clean() { + local v + v=$(printf '%s' "$1" | tr '\t\n\r' ' ') + case "$v" in + =*|+*|-*|@*) printf "'%s" "$v" ;; + *) printf '%s' "$v" ;; + esac +} +printf '%s\t%s\t%s\t%s\t%s\t%s\n' \ + "$ts" "$(clean "$1")" "$(clean "$2")" "$(clean "$3")" "$(clean "$4")" "$(clean "$5")" \ + >> "$logfile" diff --git a/skills/show-me-your-work b/skills/show-me-your-work new file mode 120000 index 0000000..afa32a9 --- /dev/null +++ b/skills/show-me-your-work @@ -0,0 +1 @@ +../plugins/show-me-your-work/skills/show-me-your-work \ No newline at end of file