retro

Name: retro
Author: Borda

23stars3forks

How to install retro?

borda/ai-rig/retro

$npx -y skills add Borda/AI-Rig --skill retro

Installs into the current project.

Summary

Post-run retrospective: reads .experiments/ JSONL, computes Wilcoxon significance, detects dead iterations, flags suspicious jumps, generates next-hypothesis queue for --hypothesis flag.

Files · 1

View on GitHub

SKILL.md

1	<objective>
2
3	Post-run retrospective analysis. After `/research:run` completes, reads `.experiments/state/<run-id>/experiments.jsonl`, computes statistical significance, detects dead iterations, flags suspicious metric jumps, generates learning summary with next-hypothesis queue.
4
5	NOT for: running experiments (use `/research:run`); designing experiments (use `/research:plan`); validating methodology (use `/research:judge`); verifying paper implementation (use `/research:verify`); comparing runs from different programs/goals — `--compare` valid only for same-program, same-metric runs. Read-only — never modifies code, commits, or experiment state.
6
7	</objective>
8
9	<workflow>
10
11	## Agent Resolution
12
13	Agent resolution: load and follow the protocol below. Contains: foundry check + fallback table. `research:scientist` in same plugin — no fallback needed if research plugin installed.
14	```bash
15	_RESEARCH_SHARED=$(python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_research}/bin/resolve_shared.py" 2>/dev/null) # timeout: 5000
16	[ -z "$_RESEARCH_SHARED" ] && { echo "! Plugin path resolution failed — ensure research plugin installed and CLAUDE_PLUGIN_ROOT set, or invoke /research:retro from project root."; exit 1; }
17	cat "$_RESEARCH_SHARED/agent-resolution.md"
18	```
19
20	## Retro Mode (Steps T1–T7)
21
22	Triggered by `retro`, `retro <run-id>`, or `retro <run-id> --compare <run-id-2>`.
23
24	Defaults: `--threshold 0.001`, `--alpha 0.05`.
25
26	Unsupported flag check: load and follow the protocol below. Supported flags for this skill: `--compare`, `--threshold`, `--alpha`.
27	```bash
28	# loads: unsupported-flag-protocol.md
29	_RESEARCH_SHARED=$(python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_research}/bin/resolve_shared.py" 2>/dev/null) # timeout: 5000
30	cat "$_RESEARCH_SHARED/unsupported-flag-protocol.md"
31	```
32
33	Task tracking: create tasks for T1–T7 at start — before any tool calls.
34
35	### Step T1: Locate and load run data
36
37	Input resolution (priority order):
38
39	1. Explicit `<run-id>` arg → read `.experiments/state/<run-id>/`
40	2. No arg → scan `.experiments/state/`, pick latest dir where `state.json` has `status: completed` or `status: goal-achieved`
41	3. None found → stop with error:
42	```text
43	No completed run found. Run /research:run first, or provide: /research:retro <run-id>
44	```
45
46	Newer-in-progress check (only when path 2 used — no explicit run-id given): after selecting completed run, scan `.experiments/state/` for any dir with `status: running` and mtime newer than selected dir. If found, surface warning but don't stop — user may intentionally retro prior completed run:
47
48	```text
49	⚠ Newer in-progress run found: <newer-run-id> (status: running, started <ISO timestamp>). Retro will analyse <selected-run-id> instead. Use /research:retro <run-id> to override.
50	```
51
52	Load files from `.experiments/state/<run-id>/`:
53
54	- `state.json`: extract `goal`, `best_metric`, `config` (incl. `metric.direction`), `iteration` count, `best_commit`. Compute `baseline_metric` from iteration 0 in `experiments.jsonl`.
55	- `experiments.jsonl`: full iteration history — validate each line parses as JSON. If last line truncated, warn and rewrite sanitized copy to `$RUN_DIR/experiments-clean.jsonl` (skip truncated last line). All downstream steps (T2 retro_analyze.py, T3 dead-iter scan, T5 scientist) must read sanitized copy — never raw file — so every step sees same iteration set. Persist sanitized path: `echo "$RUN_DIR/experiments-clean.jsonl" > "${TMPDIR:-/tmp}/retro-jsonl-path-${CSID}"` (consumers re-hydrate from this file). If JSONL untruncated, sanitized copy byte-identical to raw file.
56	- `diary.md`: if present, read for qualitative context in T5.
57
58	If `--compare <run-id-2>` present: load second run identically from `.experiments/state/<run-id-2>/`. If not found, stop: `"Compare target not found: .experiments/state/<run-id-2>/. Check run ID and retry."`
59
60	Assign `RUN_ID_ARG` from `$ARGUMENTS` — first positional non-flag token, empty if absent (ADV-H17):
61
62	```bash
63	export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
64	_REMAINDER=$(echo "$ARGUMENTS" \| sed -E 's/--compare[= ]+[^ ]+//g; s/--threshold[= ]+[^ ]+//g; s/--alpha[= ]+[^ ]+//g')
65	RUN_ID_ARG=$(echo "$_REMAINDER" \| awk '{for (i=1; i<=NF; i++) if ($i !~ /^--/) { print $i; exit }}')
66	RUN_ID_ARG="${RUN_ID_ARG:-}"
67	echo "$RUN_ID_ARG" > "${TMPDIR:-/tmp}/retro-run-id-${CSID}" # persist for T3 (vars lost between Bash calls)
68	```
69
70	Pre-compute run directory — also fix `$RUN_ID` (resolved from input resolution above), persist `$RUN_DIR` for T3 (ADV-H18 + ADV-L16):
71
72	```bash
73	export CSID

People who liked this also viewed

6 picks

Type

lark-drive飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sSkillsJul 2026382k16k
lark-sharedUse for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handlingSkillsJul 2026382k16k
lark-whiteboard飞书画板：查询和编辑飞书云文档中的画板。支持导出画板为预览图片、导出原始节点结构、使用多种格式更新画板内容。当用户需要查看画板内容、导出画板图片、编辑画板时使用此 skill。不负责：飞书云文档内容编辑（lark-doc）、文档内嵌电子表格/Base（lark-sheets / lark-base）。SkillsJul 2026380k16k
lark-task飞书任务：管理任务、清单和任务智能体。创建待办任务、查看和更新任务状态、拆分子任务、组织任务清单、分配协作成员、上传任务附件、注册或注销任务智能体、更新任务智能体的主页数据、写入智能体任务记录。当用户需要创建待办事项、查看任务列表、跟踪任务进度、管理项目清单或给他人分配任务、为任务上传附件文件、注册注销任务智能体、更新智能体主页数据、写入任务记录时使用。SkillsJul 2026380k16k
lark-attendance飞书考勤打卡：查询自己的考勤打卡记录SkillsJul 2026330k16k
lark-apps妙搭（Spark/Miaoda）应用开发与托管：应用创建、本地全栈开发、云端生成迭代、创意设计（UI mockup / 可交互原型 / 线框图 / 落地页 / 仪表盘 / 幻灯片 deck / 视觉探索）、AI相关能力和飞书平台能力或者其他外部能力集成、日志/Trace/监控指标/PV/UV 查询、环境变量管理、应用角色与成员管理、自动化触发器（定时/记录变更/Webhook/飞书审批）。当用户要SkillsJul 2026227k16k

retro

23stars3forks

View on GitHub

How to install retro?

borda/ai-rig/retro

$npx -y skills add Borda/AI-Rig --skill retro

Installs into the current project.

Summary

Post-run retrospective: reads .experiments/ JSONL, computes Wilcoxon significance, detects dead iterations, flags suspicious jumps, generates next-hypothesis queue for --hypothesis flag.

Files · 1

View on GitHub

SKILL.md

1	<objective>
2
3	Post-run retrospective analysis. After `/research:run` completes, reads `.experiments/state/<run-id>/experiments.jsonl`, computes statistical significance, detects dead iterations, flags suspicious metric jumps, generates learning summary with next-hypothesis queue.
4
5	NOT for: running experiments (use `/research:run`); designing experiments (use `/research:plan`); validating methodology (use `/research:judge`); verifying paper implementation (use `/research:verify`); comparing runs from different programs/goals — `--compare` valid only for same-program, same-metric runs. Read-only — never modifies code, commits, or experiment state.
6
7	</objective>
8
9	<workflow>
10
11	## Agent Resolution
12
13	Agent resolution: load and follow the protocol below. Contains: foundry check + fallback table. `research:scientist` in same plugin — no fallback needed if research plugin installed.
14	```bash
15	_RESEARCH_SHARED=$(python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_research}/bin/resolve_shared.py" 2>/dev/null) # timeout: 5000
16	[ -z "$_RESEARCH_SHARED" ] && { echo "! Plugin path resolution failed — ensure research plugin installed and CLAUDE_PLUGIN_ROOT set, or invoke /research:retro from project root."; exit 1; }
17	cat "$_RESEARCH_SHARED/agent-resolution.md"
18	```
19
20	## Retro Mode (Steps T1–T7)
21
22	Triggered by `retro`, `retro <run-id>`, or `retro <run-id> --compare <run-id-2>`.
23
24	Defaults: `--threshold 0.001`, `--alpha 0.05`.
25
26	Unsupported flag check: load and follow the protocol below. Supported flags for this skill: `--compare`, `--threshold`, `--alpha`.
27	```bash
28	# loads: unsupported-flag-protocol.md
29	_RESEARCH_SHARED=$(python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_research}/bin/resolve_shared.py" 2>/dev/null) # timeout: 5000
30	cat "$_RESEARCH_SHARED/unsupported-flag-protocol.md"
31	```
32
33	Task tracking: create tasks for T1–T7 at start — before any tool calls.
34
35	### Step T1: Locate and load run data
36
37	Input resolution (priority order):
38
39	1. Explicit `<run-id>` arg → read `.experiments/state/<run-id>/`
40	2. No arg → scan `.experiments/state/`, pick latest dir where `state.json` has `status: completed` or `status: goal-achieved`
41	3. None found → stop with error:
42	```text
43	No completed run found. Run /research:run first, or provide: /research:retro <run-id>
44	```
45
46	Newer-in-progress check (only when path 2 used — no explicit run-id given): after selecting completed run, scan `.experiments/state/` for any dir with `status: running` and mtime newer than selected dir. If found, surface warning but don't stop — user may intentionally retro prior completed run:
47
48	```text
49	⚠ Newer in-progress run found: <newer-run-id> (status: running, started <ISO timestamp>). Retro will analyse <selected-run-id> instead. Use /research:retro <run-id> to override.
50	```
51
52	Load files from `.experiments/state/<run-id>/`:
53
54	- `state.json`: extract `goal`, `best_metric`, `config` (incl. `metric.direction`), `iteration` count, `best_commit`. Compute `baseline_metric` from iteration 0 in `experiments.jsonl`.
55	- `experiments.jsonl`: full iteration history — validate each line parses as JSON. If last line truncated, warn and rewrite sanitized copy to `$RUN_DIR/experiments-clean.jsonl` (skip truncated last line). All downstream steps (T2 retro_analyze.py, T3 dead-iter scan, T5 scientist) must read sanitized copy — never raw file — so every step sees same iteration set. Persist sanitized path: `echo "$RUN_DIR/experiments-clean.jsonl" > "${TMPDIR:-/tmp}/retro-jsonl-path-${CSID}"` (consumers re-hydrate from this file). If JSONL untruncated, sanitized copy byte-identical to raw file.
56	- `diary.md`: if present, read for qualitative context in T5.
57
58	If `--compare <run-id-2>` present: load second run identically from `.experiments/state/<run-id-2>/`. If not found, stop: `"Compare target not found: .experiments/state/<run-id-2>/. Check run ID and retry."`
59
60	Assign `RUN_ID_ARG` from `$ARGUMENTS` — first positional non-flag token, empty if absent (ADV-H17):
61
62	```bash
63	export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
64	_REMAINDER=$(echo "$ARGUMENTS" \| sed -E 's/--compare[= ]+[^ ]+//g; s/--threshold[= ]+[^ ]+//g; s/--alpha[= ]+[^ ]+//g')
65	RUN_ID_ARG=$(echo "$_REMAINDER" \| awk '{for (i=1; i<=NF; i++) if ($i !~ /^--/) { print $i; exit }}')
66	RUN_ID_ARG="${RUN_ID_ARG:-}"
67	echo "$RUN_ID_ARG" > "${TMPDIR:-/tmp}/retro-run-id-${CSID}" # persist for T3 (vars lost between Bash calls)
68	```
69
70	Pre-compute run directory — also fix `$RUN_ID` (resolved from input resolution above), persist `$RUN_DIR` for T3 (ADV-H18 + ADV-L16):
71
72	```bash
73	export CSID

People who liked this also viewed

6 picks

Type