distill

Name: distill
Author: Borda

23stars3forks

How to install distill?

borda/ai-rig/distill

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

Installs into the current project.

Summary

One-time snapshot extracting patterns from work history and accumulated lessons, distills into concrete improvements — new agent/skill suggestions, memory pruning, consolidating lessons into rules/agent updates, or performing bin/ extraction from /audit --efficiency candidates. R

Files · 1

View on GitHub

SKILL.md

1	<objective>
2
3	Analyze how Claude Code is used and surface concrete improvements — new agents/skills to reduce repetition, or consolidate lessons into governance files (rules, agent instructions, skill updates) — without duplicating what exists.
4
5	NOT for single-file edits or quality checks — use `/foundry:audit` for config quality checks.
6	NOT for audit-only scan for extraction candidates (use `/foundry:audit --efficiency` instead of `distill executables` for detection-only).
7
8	</objective>
9
10	<inputs>
11
12	- $ARGUMENTS: optional. Modes:
13	- Omitted — analyze existing patterns and agents; generate suggestions proactively.
14	- `prune [--eager]` — evaluate project memory file for stale, redundant, or verbose entries. Default: advisory diff + apply prompt. `--eager`: score every entry (Usage likelihood × Impact → Tier P0/P1/P2), print full scored table with `#` column, let user select by tier or item numbers, delegate edits to `foundry:curator`.
15	- `memory [--eager]` — read `.notes/lessons.md` and memory feedback files, distill recurring patterns into proposed rule files, agent instruction updates, and skill workflow changes. `--eager`: include Pattern count, Strength, and Tier columns in proposal table; let user select clusters to promote by tier or item numbers; delegate writes to `foundry:curator`.
16	- `external <source> [--eager]` — analyse external plugin, skill, or agentic resource and produce structured adoption proposal. `<source>` is URL, file path, or local directory. `--eager`: lower adoption bar — recommend partial adoption even for single useful components.
17	- `executables [--eager] [<run-dir-or-report-path>]` — perform bin/ extraction from `/foundry:audit --efficiency` Check 33 candidates. Auto-detects latest run dir under `.reports/audit/`; pass optional path to target a specific run dir or report file. Runs inline Check 33 scan when no report exists. Default gates on HIGH/MEDIUM verdict. `--eager`: also surface LOW verdict clusters as extraction candidates. Spawns `foundry:sw-engineer` per cluster. Skip to Mode: Executables Extraction below.
18	- `[--eager] <recurring task description>` — use description as context when generating suggestions. `--eager`: lower frequency threshold from 3+ to 2+ occurrences; single high-effort occurrence also qualifies.
19	- `--project` — in `prune` and `memory` modes, show an interactive project picker: enumerate all slugs under `~/.claude/projects//memory/` with MEMORY.md size in tokens, then let user select which project(s) to operate on. Omit to operate across all* projects automatically. Has no effect on other modes.
20
21	</inputs>
22
23	<compaction>
24	Key boundary 1: end of Step 2 frequency heuristics (default mode only — prune/memory/external/executables exit early), before Step 3 gap analysis.
25	Preserve at boundary 1: EAGER flag, ARGUMENTS (stripped), no run-dir (default mode is stateless).
26	Terminal paths: end of Step 5 report (default mode); end of Memory Pruning mode (both eager and standard branches).
27	</compaction>
28
29	<workflow>
30
31	Task hygiene: load and follow the protocol below.
32	```bash
33	# loads: compaction-contract.md
34	# audit-skip: resilience-replication
35	_FS=$(python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_foundry}/bin/resolve_shared_path.py" foundry skills/_shared 2>/dev/null \|\| echo "plugins/cc_foundry/skills/_shared") # timeout: 5000
36	cat "$_FS/task-hygiene.md"
37	```
38
39	```bash
40	export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
41	KEEP_ITEMS=""
42	if [[ "$ARGUMENTS" =~ --keep[[:space:]]\"([^\"]+)\" ]]; then
43	KEEP_ITEMS="${BASH_REMATCH[1]}"
44	fi
45	ARGUMENTS=$(echo "$ARGUMENTS" \| sed 's/--keep "[^"]*"//g')
46	rm -f .temp/state/skill-contract.md # clear stale contract (compaction-contract.md §Lifecycle) # timeout: 5000
47	mkdir -p "${TMPDIR:-/tmp}/distill-state-${CSID}"
48	echo "$KEEP_ITEMS" > "${TMPDIR:-/tmp}/distill-state-${CSID}/keep-items"
49	EAGER=false
50	[[ "$ARGUMENTS" == "--eager" ]] && EAGER=true
51	ARGUMENTS=$(echo "$ARGUMENTS" \| sed 's/--eager//g' \| xargs) # timeout: 3000
52	echo "EAGER=$EAGER" # shell vars don't persist across Bash calls — read from stdout
53	echo "ARGUMENTS_STRIPPED=$ARGUMENTS"
54	```
55
56	> Note: `EAGER` and stripped `ARGUMENTS` are set by this Bash block, but shell variable state does not persist across separate Bash() tool calls. After this block runs, read its

People who liked this also viewed

6 picks

Type

distill

23stars3forks

View on GitHub

How to install distill?

borda/ai-rig/distill

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	<objective>
2
3	Analyze how Claude Code is used and surface concrete improvements — new agents/skills to reduce repetition, or consolidate lessons into governance files (rules, agent instructions, skill updates) — without duplicating what exists.
4
5	NOT for single-file edits or quality checks — use `/foundry:audit` for config quality checks.
6	NOT for audit-only scan for extraction candidates (use `/foundry:audit --efficiency` instead of `distill executables` for detection-only).
7
8	</objective>
9
10	<inputs>
11
12	- $ARGUMENTS: optional. Modes:
13	- Omitted — analyze existing patterns and agents; generate suggestions proactively.
14	- `prune [--eager]` — evaluate project memory file for stale, redundant, or verbose entries. Default: advisory diff + apply prompt. `--eager`: score every entry (Usage likelihood × Impact → Tier P0/P1/P2), print full scored table with `#` column, let user select by tier or item numbers, delegate edits to `foundry:curator`.
15	- `memory [--eager]` — read `.notes/lessons.md` and memory feedback files, distill recurring patterns into proposed rule files, agent instruction updates, and skill workflow changes. `--eager`: include Pattern count, Strength, and Tier columns in proposal table; let user select clusters to promote by tier or item numbers; delegate writes to `foundry:curator`.
16	- `external <source> [--eager]` — analyse external plugin, skill, or agentic resource and produce structured adoption proposal. `<source>` is URL, file path, or local directory. `--eager`: lower adoption bar — recommend partial adoption even for single useful components.
17	- `executables [--eager] [<run-dir-or-report-path>]` — perform bin/ extraction from `/foundry:audit --efficiency` Check 33 candidates. Auto-detects latest run dir under `.reports/audit/`; pass optional path to target a specific run dir or report file. Runs inline Check 33 scan when no report exists. Default gates on HIGH/MEDIUM verdict. `--eager`: also surface LOW verdict clusters as extraction candidates. Spawns `foundry:sw-engineer` per cluster. Skip to Mode: Executables Extraction below.
18	- `[--eager] <recurring task description>` — use description as context when generating suggestions. `--eager`: lower frequency threshold from 3+ to 2+ occurrences; single high-effort occurrence also qualifies.
19	- `--project` — in `prune` and `memory` modes, show an interactive project picker: enumerate all slugs under `~/.claude/projects//memory/` with MEMORY.md size in tokens, then let user select which project(s) to operate on. Omit to operate across all* projects automatically. Has no effect on other modes.
20
21	</inputs>
22
23	<compaction>
24	Key boundary 1: end of Step 2 frequency heuristics (default mode only — prune/memory/external/executables exit early), before Step 3 gap analysis.
25	Preserve at boundary 1: EAGER flag, ARGUMENTS (stripped), no run-dir (default mode is stateless).
26	Terminal paths: end of Step 5 report (default mode); end of Memory Pruning mode (both eager and standard branches).
27	</compaction>
28
29	<workflow>
30
31	Task hygiene: load and follow the protocol below.
32	```bash
33	# loads: compaction-contract.md
34	# audit-skip: resilience-replication
35	_FS=$(python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_foundry}/bin/resolve_shared_path.py" foundry skills/_shared 2>/dev/null \|\| echo "plugins/cc_foundry/skills/_shared") # timeout: 5000
36	cat "$_FS/task-hygiene.md"
37	```
38
39	```bash
40	export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
41	KEEP_ITEMS=""
42	if [[ "$ARGUMENTS" =~ --keep[[:space:]]\"([^\"]+)\" ]]; then
43	KEEP_ITEMS="${BASH_REMATCH[1]}"
44	fi
45	ARGUMENTS=$(echo "$ARGUMENTS" \| sed 's/--keep "[^"]*"//g')
46	rm -f .temp/state/skill-contract.md # clear stale contract (compaction-contract.md §Lifecycle) # timeout: 5000
47	mkdir -p "${TMPDIR:-/tmp}/distill-state-${CSID}"
48	echo "$KEEP_ITEMS" > "${TMPDIR:-/tmp}/distill-state-${CSID}/keep-items"
49	EAGER=false
50	[[ "$ARGUMENTS" == "--eager" ]] && EAGER=true
51	ARGUMENTS=$(echo "$ARGUMENTS" \| sed 's/--eager//g' \| xargs) # timeout: 3000
52	echo "EAGER=$EAGER" # shell vars don't persist across Bash calls — read from stdout
53	echo "ARGUMENTS_STRIPPED=$ARGUMENTS"
54	```
55
56	> Note: `EAGER` and stripped `ARGUMENTS` are set by this Bash block, but shell variable state does not persist across separate Bash() tool calls. After this block runs, read its

People who liked this also viewed

6 picks

Type