@olegkoval/agent-skills 1.10.1 → 1.11.0

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "olko-agent-skills",
   "description": "Agent-agnostic skill catalog for Codex, Claude, Cursor, and other skill-aware tools.",
-  "version": "1.10.0",
+  "version": "1.10.1",
   "author": {
     "name": "Oleg Koval"
   },
@@ -18,6 +18,7 @@
     "./packages/music/fill-music-player",
     "./packages/software-development/product-builder",
     "./packages/software-development/starter-rules",
+    "./packages/software-development/review-past-performance",
     "./packages/software-development/open-source-publisher",
     "./packages/marketing/viral-launch",
     "./packages/marketing/search-console-indexing-audit",

package/.cursor-plugin/index.json

@@ -46,6 +46,11 @@
       "source": "./packages/software-development/starter-rules/adapters/cursor",
       "description": "Load and enforce hard rules for every oleg-koval/* starter: 300-line files, E2E tests, pre-commit hooks, Vertical Slice architecture, no comments, KISS/DRY/SOLID."
     },
+    {
+      "name": "olko:review-past-performance",
+      "source": "./packages/software-development/review-past-performance/adapters/cursor",
+      "description": "Self-improvement loop that pulls the last 24h of ICM memories, git history, and skill analytics to detect repeated mistakes, slow workflows, and missing coverage, then proposes 1-3 concrete improvements."
+    },
     {
       "name": "olko:open-source-publisher",
       "source": "./packages/software-development/open-source-publisher/adapters/cursor",

package/.kiro/steering/review-past-performance.md

@@ -0,0 +1,202 @@
+<!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
+
+---
+inclusion: manual
+description: "Self-improvement loop that pulls the last 24h of ICM memories, git history, and skill analytics to detect repeated mistakes, slow workflows, and missing coverage, then proposes 1-3 concrete improvements."
+---
+
+
+# /review-past-performance
+
+Self-improvement loop. Analyze recent sessions, find durable patterns, propose fixes.
+
+## Step 1 — Gather raw signals (run in parallel)
+
+```bash
+# A: ICM memories from last 24h
+icm recall "mistakes errors repeated workflow" --limit 10 2>/dev/null || echo "ICM_UNAVAILABLE"
+icm recall "completed task feature fix" --limit 10 2>/dev/null || echo "ICM_UNAVAILABLE"
+```
+
+```bash
+# B: Git activity last 24h across all repos the user works in
+git log --all --since="24 hours ago" --oneline --author="$(git config user.email 2>/dev/null)" 2>/dev/null | head -30 || echo "NO_GIT"
+```
+
+```bash
+# C: ICM transcripts (last 3 sessions)
+icm transcript search "" --limit 3 2>/dev/null || echo "TRANSCRIPTS_UNAVAILABLE"
+```
+
+```bash
+# D: Skill usage from gstack analytics (what skills were run, outcomes)
+tail -50 ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null | jq -c 'select(.ts > (now - 86400 | todate))' 2>/dev/null || \
+  tail -50 ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null | head -20 || echo "NO_ANALYTICS"
+```
+
+```bash
+# E: ICM errors-resolved topic (what broke and was fixed)
+icm recall "error" -t "errors-resolved" --limit 5 2>/dev/null || echo "NO_ERROR_MEMORIES"
+```
+
+```bash
+# F: Recent learnings (gstack)
+_GSTACK_HOME="${GSTACK_HOME:-$HOME/.gstack}"
+eval "$($HOME/.slate/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="$_GSTACK_HOME/projects/${SLUG:-unknown}/learnings.jsonl"
+[ -f "$_LEARN_FILE" ] && tail -20 "$_LEARN_FILE" || echo "NO_LEARNINGS"
+```
+
+## Step 2 — Synthesize patterns
+
+Read all signals. Classify findings into these categories:
+
+**Repeated mistakes** — same error, same fix, same confusion appearing more than once in the signals. E.g., always forgetting to handle null on a specific field, always hitting the same linting error.
+
+**Slow workflows** — multi-step sequences that took many tool calls but could be a single skill. E.g., always doing manual `git log` + `grep` + read 3 files before every PR review.
+
+**Missing coverage** — areas where work was done but no test was written or no memory was stored.
+
+**Underused skills** — skills that would have applied but were not invoked (check skill-usage.jsonl gaps vs. git activity).
+
+**Knowledge gaps** — concepts that came up repeatedly as questions or confusion.
+
+Score each finding:
+- **Frequency**: how many times it appeared (1 = once, 3 = three or more)
+- **Time cost**: rough estimate per occurrence (minutes)
+- **Fixability**: easy (a new skill/memory fixes it), medium (needs a process change), hard (structural)
+
+Pick the top 1-3 findings by `frequency × time_cost × fixability_inverse`.
+
+## Step 3 — Formulate proposals
+
+For each finding, produce exactly one proposal. Proposal types:
+
+**Type A — New skill**: The repeated sequence can be codified. Provide:
+- Proposed skill name (lowercase, dashes, ≤32 chars)
+- Trigger phrases (3-5)
+- 5-8 line SKILL.md workflow skeleton
+- Estimated time savings per occurrence
+
+**Type B — Skill tweak**: An existing skill is close but missing a step or check. Provide:
+- Which skill (`/skill-name`)
+- What specific text to add/change (before/after diff)
+- Why this covers the gap
+
+**Type C — ICM memory / eval criteria**: A pattern should be captured as a durable memory or eval rule. Provide:
+- `icm store` command (with topic, content, importance)
+- Or: a yes/no eval question to add to an existing skill
+
+## Step 4 — Present findings (D1)
+
+Use AskUserQuestion:
+
+```
+D1 — Performance review: N patterns found, N proposals
+Project/branch/task: 24h session review — git, ICM memories, skill analytics.
+ELI10: I looked at your last 24 hours of work: git commits, ICM memories,
+skill runs, and resolved errors. Here's what I found repeating and what
+I'd do about it. Approve proposals individually or skip any.
+Stakes if we pick wrong: skipping a proposal leaves the pattern unfixed;
+approving a bad proposal adds noise. You can always /skillify or rm a skill later.
+Recommendation: A — review each proposal and approve what resonates.
+Note: options differ in kind, not coverage — no completeness score.
+A) Walk me through each proposal (recommended)
+B) Show summary only, I'll decide what to dig into
+C) Abort — nothing to act on today
+```
+
+If B: print a one-line summary table (proposal number, type, finding, estimated savings). Stop.
+
+If C: print "No changes made. Run /review-past-performance again anytime." Stop.
+
+If A: proceed to Step 5.
+
+## Step 5 — Proposal gate (one per proposal)
+
+For each proposal (D2, D3, D4 ...):
+
+Print:
+```
+--- Proposal N of N ---
+Finding: <one sentence>
+Pattern evidence: <which signals showed this>
+Proposal type: <A/B/C>
+<full proposal detail from Step 3>
+Estimated savings: ~X min/occurrence
+```
+
+Then AskUserQuestion:
+
+```
+D<N> — Apply proposal N: <short title>?
+Project/branch/task: <finding in one sentence>
+ELI10: <plain English: what this proposes, what changes, what you gain>
+Stakes if we pick wrong: <what happens if you apply a bad one, or skip a good one>
+Recommendation: A — apply it — the evidence is clear enough to try it.
+Note: options differ in kind, not coverage — no completeness score.
+A) Apply this proposal (recommended)
+B) Skip this one
+C) Modify before applying (describe what to change)
+```
+
+If C: ask what to change, update the proposal in-memory, re-show, re-ask A/B only.
+
+## Step 6 — Execute approved proposals
+
+For each approved proposal:
+
+**Type A (new skill):**
+```bash
+mkdir -p ~/.claude/skills/<name>
+```
+Write `~/.claude/skills/<name>/SKILL.md` with the skeleton from Step 3.
+Print: "Skill /<name> created at ~/.claude/skills/<name>/SKILL.md — invoke it with /<name>."
+
+**Type B (skill tweak):**
+Read the target skill file. Apply the diff. Print the before/after. Do NOT commit.
+
+**Type C (ICM memory):**
+```bash
+icm store -t "<topic>" -c "<content>" -i <importance> -k "<keywords>"
+```
+Print the stored memory ID.
+
+## Step 7 — Summary
+
+After all proposals are processed, print a compact summary:
+
+```
+/review-past-performance complete
+Applied: N proposals
+Skipped: N proposals
+
+What changed:
+- [list each applied change with one line]
+
+Run again tomorrow: /review-past-performance
+```
+
+Then:
+```bash
+# Store this review run as an ICM memory so future reviews have continuity
+icm store -t "context-workflow" \
+  -c "Performance review $(date +%Y-%m-%d): found [N] patterns, applied [N] proposals. Key findings: [one-line summary]" \
+  -i medium \
+  -k "performance-review,self-improvement" 2>/dev/null || true
+```
+
+```bash
+# Log to gstack timeline if available
+~/.slate/skills/gstack/bin/gstack-timeline-log \
+  '{"skill":"review-past-performance","event":"completed","outcome":"success"}' 2>/dev/null || true
+```
+
+---
+
+## Notes
+
+- This skill reads only — no git mutations, no PR actions, no Notion/Linear writes.
+- Type A skills created here are skeletons. Run them once and tune before relying on them.
+- If ICM is unavailable (`ICM_UNAVAILABLE`), fall back to git log + gstack analytics only; note the limitation in findings.
+- If there are fewer than 3 signals available, say so and offer to run again after more sessions.

package/.windsurf/rules/review-past-performance.md

@@ -0,0 +1,201 @@
+<!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
+
+---
+description: "Self-improvement loop that pulls the last 24h of ICM memories, git history, and skill analytics to detect repeated mistakes, slow workflows, and missing coverage, then proposes 1-3 concrete improvements."
+---
+
+
+# /review-past-performance
+
+Self-improvement loop. Analyze recent sessions, find durable patterns, propose fixes.
+
+## Step 1 — Gather raw signals (run in parallel)
+
+```bash
+# A: ICM memories from last 24h
+icm recall "mistakes errors repeated workflow" --limit 10 2>/dev/null || echo "ICM_UNAVAILABLE"
+icm recall "completed task feature fix" --limit 10 2>/dev/null || echo "ICM_UNAVAILABLE"
+```
+
+```bash
+# B: Git activity last 24h across all repos the user works in
+git log --all --since="24 hours ago" --oneline --author="$(git config user.email 2>/dev/null)" 2>/dev/null | head -30 || echo "NO_GIT"
+```
+
+```bash
+# C: ICM transcripts (last 3 sessions)
+icm transcript search "" --limit 3 2>/dev/null || echo "TRANSCRIPTS_UNAVAILABLE"
+```
+
+```bash
+# D: Skill usage from gstack analytics (what skills were run, outcomes)
+tail -50 ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null | jq -c 'select(.ts > (now - 86400 | todate))' 2>/dev/null || \
+  tail -50 ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null | head -20 || echo "NO_ANALYTICS"
+```
+
+```bash
+# E: ICM errors-resolved topic (what broke and was fixed)
+icm recall "error" -t "errors-resolved" --limit 5 2>/dev/null || echo "NO_ERROR_MEMORIES"
+```
+
+```bash
+# F: Recent learnings (gstack)
+_GSTACK_HOME="${GSTACK_HOME:-$HOME/.gstack}"
+eval "$($HOME/.slate/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="$_GSTACK_HOME/projects/${SLUG:-unknown}/learnings.jsonl"
+[ -f "$_LEARN_FILE" ] && tail -20 "$_LEARN_FILE" || echo "NO_LEARNINGS"
+```
+
+## Step 2 — Synthesize patterns
+
+Read all signals. Classify findings into these categories:
+
+**Repeated mistakes** — same error, same fix, same confusion appearing more than once in the signals. E.g., always forgetting to handle null on a specific field, always hitting the same linting error.
+
+**Slow workflows** — multi-step sequences that took many tool calls but could be a single skill. E.g., always doing manual `git log` + `grep` + read 3 files before every PR review.
+
+**Missing coverage** — areas where work was done but no test was written or no memory was stored.
+
+**Underused skills** — skills that would have applied but were not invoked (check skill-usage.jsonl gaps vs. git activity).
+
+**Knowledge gaps** — concepts that came up repeatedly as questions or confusion.
+
+Score each finding:
+- **Frequency**: how many times it appeared (1 = once, 3 = three or more)
+- **Time cost**: rough estimate per occurrence (minutes)
+- **Fixability**: easy (a new skill/memory fixes it), medium (needs a process change), hard (structural)
+
+Pick the top 1-3 findings by `frequency × time_cost × fixability_inverse`.
+
+## Step 3 — Formulate proposals
+
+For each finding, produce exactly one proposal. Proposal types:
+
+**Type A — New skill**: The repeated sequence can be codified. Provide:
+- Proposed skill name (lowercase, dashes, ≤32 chars)
+- Trigger phrases (3-5)
+- 5-8 line SKILL.md workflow skeleton
+- Estimated time savings per occurrence
+
+**Type B — Skill tweak**: An existing skill is close but missing a step or check. Provide:
+- Which skill (`/skill-name`)
+- What specific text to add/change (before/after diff)
+- Why this covers the gap
+
+**Type C — ICM memory / eval criteria**: A pattern should be captured as a durable memory or eval rule. Provide:
+- `icm store` command (with topic, content, importance)
+- Or: a yes/no eval question to add to an existing skill
+
+## Step 4 — Present findings (D1)
+
+Use AskUserQuestion:
+
+```
+D1 — Performance review: N patterns found, N proposals
+Project/branch/task: 24h session review — git, ICM memories, skill analytics.
+ELI10: I looked at your last 24 hours of work: git commits, ICM memories,
+skill runs, and resolved errors. Here's what I found repeating and what
+I'd do about it. Approve proposals individually or skip any.
+Stakes if we pick wrong: skipping a proposal leaves the pattern unfixed;
+approving a bad proposal adds noise. You can always /skillify or rm a skill later.
+Recommendation: A — review each proposal and approve what resonates.
+Note: options differ in kind, not coverage — no completeness score.
+A) Walk me through each proposal (recommended)
+B) Show summary only, I'll decide what to dig into
+C) Abort — nothing to act on today
+```
+
+If B: print a one-line summary table (proposal number, type, finding, estimated savings). Stop.
+
+If C: print "No changes made. Run /review-past-performance again anytime." Stop.
+
+If A: proceed to Step 5.
+
+## Step 5 — Proposal gate (one per proposal)
+
+For each proposal (D2, D3, D4 ...):
+
+Print:
+```
+--- Proposal N of N ---
+Finding: <one sentence>
+Pattern evidence: <which signals showed this>
+Proposal type: <A/B/C>
+<full proposal detail from Step 3>
+Estimated savings: ~X min/occurrence
+```
+
+Then AskUserQuestion:
+
+```
+D<N> — Apply proposal N: <short title>?
+Project/branch/task: <finding in one sentence>
+ELI10: <plain English: what this proposes, what changes, what you gain>
+Stakes if we pick wrong: <what happens if you apply a bad one, or skip a good one>
+Recommendation: A — apply it — the evidence is clear enough to try it.
+Note: options differ in kind, not coverage — no completeness score.
+A) Apply this proposal (recommended)
+B) Skip this one
+C) Modify before applying (describe what to change)
+```
+
+If C: ask what to change, update the proposal in-memory, re-show, re-ask A/B only.
+
+## Step 6 — Execute approved proposals
+
+For each approved proposal:
+
+**Type A (new skill):**
+```bash
+mkdir -p ~/.claude/skills/<name>
+```
+Write `~/.claude/skills/<name>/SKILL.md` with the skeleton from Step 3.
+Print: "Skill /<name> created at ~/.claude/skills/<name>/SKILL.md — invoke it with /<name>."
+
+**Type B (skill tweak):**
+Read the target skill file. Apply the diff. Print the before/after. Do NOT commit.
+
+**Type C (ICM memory):**
+```bash
+icm store -t "<topic>" -c "<content>" -i <importance> -k "<keywords>"
+```
+Print the stored memory ID.
+
+## Step 7 — Summary
+
+After all proposals are processed, print a compact summary:
+
+```
+/review-past-performance complete
+Applied: N proposals
+Skipped: N proposals
+
+What changed:
+- [list each applied change with one line]
+
+Run again tomorrow: /review-past-performance
+```
+
+Then:
+```bash
+# Store this review run as an ICM memory so future reviews have continuity
+icm store -t "context-workflow" \
+  -c "Performance review $(date +%Y-%m-%d): found [N] patterns, applied [N] proposals. Key findings: [one-line summary]" \
+  -i medium \
+  -k "performance-review,self-improvement" 2>/dev/null || true
+```
+
+```bash
+# Log to gstack timeline if available
+~/.slate/skills/gstack/bin/gstack-timeline-log \
+  '{"skill":"review-past-performance","event":"completed","outcome":"success"}' 2>/dev/null || true
+```
+
+---
+
+## Notes
+
+- This skill reads only — no git mutations, no PR actions, no Notion/Linear writes.
+- Type A skills created here are skeletons. Run them once and tune before relying on them.
+- If ICM is unavailable (`ICM_UNAVAILABLE`), fall back to git log + gstack analytics only; note the limitation in findings.
+- If there are fewer than 3 signals available, say so and offer to run again after more sessions.

package/README.md

@@ -3,7 +3,7 @@
   <p><strong>Agent-agnostic skill catalog for Codex, Claude, Cursor, Copilot, Windsurf, Kiro, and other skill-aware tools.</strong></p>
   <p>
     <img src="https://img.shields.io/badge/license-MIT-16a34a" alt="MIT license">
-    <img src="https://img.shields.io/badge/skills-18-2563eb" alt="18 skills">
+    <img src="https://img.shields.io/badge/skills-19-2563eb" alt="19 skills">
     <img src="https://img.shields.io/badge/platforms-Codex%20%7C%20Claude%20%7C%20Cursor%20%7C%20Copilot%20%7C%20Windsurf%20%7C%20Kiro-111827" alt="Codex Claude Cursor Copilot Windsurf Kiro">
     <img src="https://img.shields.io/badge/status-public%20catalog-16a34a" alt="Public catalog">
   </p>
@@ -174,7 +174,7 @@ packages/{category}/{skill}/adapters/
 
 </details>
 
-## All 18 Skills
+## All 19 Skills
 
 These packages are the entry points. Each one is a structured workflow with concrete trigger conditions and execution steps. You can reference any skill directly by its `olko:*` lookup name.
 
@@ -193,6 +193,7 @@ These packages are the entry points. Each one is a structured workflow with conc
 | [open-source-publisher](packages/software-development/open-source-publisher/SKILL.md) | Prepares an open-source repository for public publishing with branding, CI/CD, and release hygiene | Releasing a private project publicly with proper GitHub Pages, README, and social preview |
 | [obsidian-pr-sync](packages/software-development/obsidian-pr-sync/SKILL.md) | Fetches open GitHub PRs assigned to you or requesting review, and writes a grouped age-sorted section into today's Obsidian daily note | Syncing GitHub review queue to Obsidian at the start of the day or on demand |
 | [obsidian-task-rollover](packages/software-development/obsidian-task-rollover/SKILL.md) | Migrates unchecked tasks from today's Obsidian daily note to the next workday under `## Carried over`, marking source tasks as `[>]` | End-of-day bullet-journal task migration, rolling unfinished work to the next workday |
+| [review-past-performance](packages/software-development/review-past-performance/SKILL.md) | Self-improvement loop: pulls 24h of ICM memories, git history, and skill analytics; detects repeated mistakes, slow workflows, and missing coverage; proposes 1-3 concrete fixes | Reviewing a day's coding sessions for patterns, wanting to codify a repeated workflow, or running a daily self-improvement loop |
 
 ### Music
 

package/catalog/skills.json

@@ -198,6 +198,29 @@
         "kiro"
       ]
     },
+    {
+      "name": "review-past-performance",
+      "lookupName": "olko:review-past-performance",
+      "category": "software-development",
+      "path": "packages/software-development/review-past-performance",
+      "description": "Self-improvement loop that pulls the last 24h of ICM memories, git history, and skill analytics to detect repeated mistakes, slow workflows, and missing coverage, then proposes 1-3 concrete improvements.",
+      "tags": [
+        "self-improvement",
+        "performance-review",
+        "icm",
+        "skills",
+        "workflow",
+        "ai-tools"
+      ],
+      "adapters": [
+        "codex",
+        "claude",
+        "cursor",
+        "copilot",
+        "windsurf",
+        "kiro"
+      ]
+    },
     {
       "name": "open-source-publisher",
       "lookupName": "olko:open-source-publisher",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@olegkoval/agent-skills",
-  "version": "1.10.1",
+  "version": "1.11.0",
   "private": false,
   "publishConfig": {
     "access": "public"