boost-skill-cli 1.2.9__tar.gz → 1.2.11__tar.gz

{boost_skill_cli-1.2.9 → boost_skill_cli-1.2.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: boost-skill-cli
-Version: 1.2.9
+Version: 1.2.11
 Summary: boost — Homebrew for AI coding skills
 Author: Jonathan Reyes
 License: GNU GENERAL PUBLIC LICENSE

{boost_skill_cli-1.2.9 → boost_skill_cli-1.2.11}/boost_cli/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '1.2.9'
-__version_tuple__ = version_tuple = (1, 2, 9)
+__version__ = version = '1.2.11'
+__version_tuple__ = version_tuple = (1, 2, 11)
 
 __commit_id__ = commit_id = None

{boost_skill_cli-1.2.9 → boost_skill_cli-1.2.11}/boost_skill_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: boost-skill-cli
-Version: 1.2.9
+Version: 1.2.11
 Summary: boost — Homebrew for AI coding skills
 Author: Jonathan Reyes
 License: GNU GENERAL PUBLIC LICENSE

{boost_skill_cli-1.2.9 → boost_skill_cli-1.2.11}/boost_skill_cli.egg-info/SOURCES.txt

@@ -412,6 +412,7 @@ docs/roadmap/items/sync-reported-success-for-a-link-it-refused.md
 docs/roadmap/items/tap-signing-and-provenance-sigstore-minisign.md
 docs/roadmap/items/taps-check-out-freight-they-never-index.md
 docs/roadmap/items/the-catalogue-advertised-repos-that-no-longer-exist.md
+docs/roadmap/items/the-scale-corpus-refreshed-the-wrong-rows.md
 docs/roadmap/items/the-shard-job-that-could-not-finish.md
 docs/roadmap/items/theme-asset-linting-stylelint-eslint.md
 docs/roadmap/items/tool-call-eval-tier.md

boost_skill_cli-1.2.11/docs/roadmap/items/the-scale-corpus-refreshed-the-wrong-rows.md

@@ -0,0 +1,53 @@
+---
+id: the-scale-corpus-refreshed-the-wrong-rows
+board: code
+section: internals
+status: shipped
+category: CI · Evaluation
+complexity: S
+impact: High
+wow: 5
+note: 185 rows, 20 pinned — the monthly job moved exactly the 20 it did not own and pinned none of the 165 it existed to pin
+order: 121
+owner: loop/scale-refresh-freezes-required
+pr: 537
+title: the scheduled re-pin that refreshed the twenty rows it must not touch, and none of the hundred and sixty-five it existed to pin
+---
+<b>The Tier 1b scale corpus is the required corpus plus distractors</b> &mdash; 20 rows copied
+verbatim out of <code>taps.txt</code>, pins and counts included, so both tiers start from the same
+trees, plus 165 curated registries that make it the size of a real install. The golden floors were
+calibrated against those 20 trees. A scale tier measuring a <em>different</em> snapshot of the same
+repos reports a difference that is not scale.
+
+<b>The monthly job did precisely the inverse of its job.</b>
+<code>eval_corpus.py --refresh</code> walked every row of whatever file it was handed, so it moved
+the 20 required pins &mdash; which <code>build_scale_corpus.py</code> owns and copies verbatim
+&mdash; and, because <code>relock_text</code> skipped any row with fewer than two fields, pinned
+<b>zero</b> of the 165 bare distractors. The tier that exists to measure a pinned 20,000-entry
+corpus was floating on upstream HEAD for <b>89% of its rows</b>.
+
+<b>It also could never merge.</b> The same workflow runs
+<code>build_scale_corpus.py --check</code> one step <em>before</em> the refresh; the refresh then
+broke exactly that check. Every PR it opened was unmergeable by construction, and the diff read as
+ordinary pin movement &mdash; 20 SHAs and 20 counts, which is what a healthy re-pin looks like.
+PR #536 is the specimen.
+
+<b>Two mechanisms, both about a fallback being consulted too early.</b> The pins moved because
+nothing said the required rows belong to another file. The distractors stayed bare because
+<code>relock_text</code> gated on <em>&ldquo;does this row already have a pin&rdquo;</em> when the
+durable rule is <em>&ldquo;never write a count without a SHA&rdquo;</em> &mdash;
+<code>--relock</code> re-measures the same tree and has no SHA to offer, but <code>--refresh</code>
+has just resolved upstream HEAD and can close the row. A third, quieter symptom fell out of the
+first: the column width is the longest name being rewritten, and the distractor names are longer
+than anything in <code>taps.txt</code>, so every required row was re-columned even where its pin had
+not changed.
+
+<b>Freezing is by membership, not identity.</b> <code>--refresh</code> on <code>taps.txt</code>
+itself is exactly the job that <em>may</em> move those pins, so it freezes nothing. Freezing on
+&ldquo;is this a required repo&rdquo; would have made the required corpus permanently unrefreshable
+&mdash; the same bug pointed the other way, and far quieter.
+
+<b>Verified against the real file, not argued.</b> Simulating a refresh that resolved a new SHA for
+all 185 rows: the 20 required rows come back byte-identical, all 185 end up pinned, and
+<code>--check</code> passes &mdash; so the PR is mergeable. The workflow now runs that check
+<b>after</b> the refresh as well as before, which is the guard that was missing.

{boost_skill_cli-1.2.9 → boost_skill_cli-1.2.11}/docs/roadmap.html

@@ -133,7 +133,7 @@
       <div class="stat"><b>16</b><span>Shipped</span></div>
       <div class="stat"><b>1</b><span>Next up</span></div>
       <div class="stat"><b>7</b><span>Planned</span></div>
-      <div class="stat"><b>258</b><span>Loop finds</span></div>
+      <div class="stat"><b>259</b><span>Loop finds</span></div>
       <!-- /ROADMAP:stats -->
     </div>
   </section>
@@ -4255,6 +4255,56 @@ with the numbers.</p></details>
           <span class="m">5h30m cancelled at the ceiling, then 2h07m green — the same job, with duplicate embeddings collapsed</span>
         </div>
       </article>
+
+      <article class="cap rcard" id="the-scale-corpus-refreshed-the-wrong-rows">
+        <div class="head"><span class="pill shipped">Shipped</span><span class="cat">CI · Evaluation</span></div>
+        <h3>the scheduled re-pin that refreshed the twenty rows it must not touch, and none of the hundred and sixty-five it existed to pin</h3>
+        <details class="cardbody"><summary>Write-up</summary>
+        <p><b>The Tier 1b scale corpus is the required corpus plus distractors</b> &mdash; 20 rows copied
+verbatim out of <code>taps.txt</code>, pins and counts included, so both tiers start from the same
+trees, plus 165 curated registries that make it the size of a real install. The golden floors were
+calibrated against those 20 trees. A scale tier measuring a <em>different</em> snapshot of the same
+repos reports a difference that is not scale.
+
+<b>The monthly job did precisely the inverse of its job.</b>
+<code>eval_corpus.py --refresh</code> walked every row of whatever file it was handed, so it moved
+the 20 required pins &mdash; which <code>build_scale_corpus.py</code> owns and copies verbatim
+&mdash; and, because <code>relock_text</code> skipped any row with fewer than two fields, pinned
+<b>zero</b> of the 165 bare distractors. The tier that exists to measure a pinned 20,000-entry
+corpus was floating on upstream HEAD for <b>89% of its rows</b>.
+
+<b>It also could never merge.</b> The same workflow runs
+<code>build_scale_corpus.py --check</code> one step <em>before</em> the refresh; the refresh then
+broke exactly that check. Every PR it opened was unmergeable by construction, and the diff read as
+ordinary pin movement &mdash; 20 SHAs and 20 counts, which is what a healthy re-pin looks like.
+PR #536 is the specimen.
+
+<b>Two mechanisms, both about a fallback being consulted too early.</b> The pins moved because
+nothing said the required rows belong to another file. The distractors stayed bare because
+<code>relock_text</code> gated on <em>&ldquo;does this row already have a pin&rdquo;</em> when the
+durable rule is <em>&ldquo;never write a count without a SHA&rdquo;</em> &mdash;
+<code>--relock</code> re-measures the same tree and has no SHA to offer, but <code>--refresh</code>
+has just resolved upstream HEAD and can close the row. A third, quieter symptom fell out of the
+first: the column width is the longest name being rewritten, and the distractor names are longer
+than anything in <code>taps.txt</code>, so every required row was re-columned even where its pin had
+not changed.
+
+<b>Freezing is by membership, not identity.</b> <code>--refresh</code> on <code>taps.txt</code>
+itself is exactly the job that <em>may</em> move those pins, so it freezes nothing. Freezing on
+&ldquo;is this a required repo&rdquo; would have made the required corpus permanently unrefreshable
+&mdash; the same bug pointed the other way, and far quieter.
+
+<b>Verified against the real file, not argued.</b> Simulating a refresh that resolved a new SHA for
+all 185 rows: the 20 required rows come back byte-identical, all 185 end up pinned, and
+<code>--check</code> passes &mdash; so the PR is mergeable. The workflow now runs that check
+<b>after</b> the refresh as well as before, which is the guard that was missing.</p></details>
+        <div class="meta">
+          <span class="m">Complexity <b>S</b></span>
+          <span class="m hi">Impact <b>High</b></span>
+          <span class="m">Wow <b class="wow">★★★★★</b></span>
+          <span class="m">185 rows, 20 pinned — the monthly job moved exactly the 20 it did not own and pinned none of the 165 it existed to pin</span>
+        </div>
+      </article>
       <!-- /ROADMAP:cards -->
 
     </div>

{boost_skill_cli-1.2.9 → boost_skill_cli-1.2.11}/scripts/eval_corpus.py

@@ -77,7 +77,7 @@ import argparse
 import re
 import subprocess
 import sys
-from collections.abc import Sequence
+from collections.abc import Collection, Sequence
 from pathlib import Path
 
 ROOT = Path(__file__).resolve().parent.parent
@@ -346,31 +346,50 @@ def _report_failures(failures: Sequence[CorpusError], total_rows: int) -> int:
 
 
 def relock_text(text: str, counts: dict[str, int],
-                shas: dict[str, str] | None = None) -> str:
+                shas: dict[str, str] | None = None,
+                frozen: Collection[str] | None = None) -> str:
     """Rewrite each pinned row's entry count — and its SHA when ``shas`` says so.
 
     A whole-file rewrite would lose the header, which is where the reasoning
-    lives; this touches only rows it has a new count for. A row with no SHA is
-    left alone — a count beside an unpinned repo describes a tree free to change
-    underneath it, so it must never be written.
+    lives; this touches only rows it has a new count for. A count is never
+    written without a SHA — beside an unpinned repo it would describe a tree
+    free to change underneath it — but the SHA may come from ``shas`` rather
+    than from the row, which is how ``--refresh`` closes a row that arrived
+    bare. Gating on "the row already has a pin" instead left the scale corpus
+    at 165 bare rows to 20 pinned, refreshing only the 20 it did not own.
 
     ``shas`` is what makes ``--refresh`` a rewrite of the pins rather than of
     the counts alone. It is optional because the two operations are genuinely
     different: ``--relock`` re-measures the *same* trees (the scanner changed),
     ``--refresh`` moves to *new* trees (the world changed).
+
+    ``frozen`` names repos whose rows this file does not own, and they are
+    emitted byte for byte — not re-pinned, and *not re-columned*. Both halves
+    matter: the width is the longest name being rewritten, so refreshing
+    ``taps-scale.txt`` (whose distractor names are longer than anything in
+    ``taps.txt``) moved every required row even where its pin had not changed.
     """
     shas = shas or {}
-    width = max([len(r) for r in counts] or [1])
+    frozen = frozen or ()
+    width = max([len(r) for r in counts if r not in frozen] or [1])
     out = []
     for raw in text.splitlines():
         line = raw.strip()
         parts = line.split()
-        if not line or line.startswith("#") or len(parts) < 2 \
-                or parts[0] not in counts or not _SHA.fullmatch(parts[1]):
+        if not line or line.startswith("#") or not parts \
+                or parts[0] not in counts or parts[0] in frozen:
             out.append(raw)
             continue
         repo = parts[0]
-        sha = shas.get(repo, parts[1])
+        # The row's own pin is only a fallback, and only when well formed: a
+        # malformed one is not a value to carry forward, it is a row nothing
+        # may claim to have measured.
+        committed = (parts[1] if len(parts) > 1
+                     and _SHA.fullmatch(parts[1]) else None)
+        sha = shas.get(repo) or committed
+        if sha is None:
+            out.append(raw)
+            continue
         if not _SHA.fullmatch(sha):
             raise SystemExit(
                 "refusing to write %s: %r is not a 40-character commit SHA"
@@ -379,6 +398,27 @@ def relock_text(text: str, counts: dict[str, int],
     return "\n".join(out) + ("\n" if text.endswith("\n") else "")
 
 
+def frozen_rows(taps: Path, required: Path = DEFAULT_TAPS) -> set[str]:
+    """Repos in ``taps`` whose pins belong to ``required``, not to ``taps``.
+
+    The scale corpus is the required corpus PLUS distractors, and
+    ``build_scale_corpus.render`` copies the required block in verbatim so both
+    tiers start from the same trees. The golden floors were calibrated against
+    those trees; a scale tier measuring a *different* snapshot of the same
+    repos reports a difference that is not scale.
+
+    Membership, not identity, decides. ``--refresh`` on ``taps.txt`` itself is
+    exactly the job that MAY move those pins, so it must freeze nothing —
+    freezing on "is this a required repo" rather than "does another file own
+    this row" would make the required corpus permanently unrefreshable, which
+    is the same bug pointed the other way and far quieter.
+    """
+    if taps.resolve() == required.resolve() or not required.exists():
+        return set()
+    return {repo for repo, _sha, _n in
+            parse_taps(required.read_text(encoding="utf-8"))}
+
+
 def refresh_summary(rows: Sequence[Row], shas: dict[str, str],
                     counts: dict[str, int]) -> str:
     """A Markdown table of what a refresh moved, for the pull request body.
@@ -465,10 +505,20 @@ def _refresh(taps: Path, summary_path: str | None = None) -> int:
     from boost_cli.core import catalog, gitutil, registry  # deferred: path shim
 
     rows = parse_taps(taps.read_text(encoding="utf-8"))
+    # Rows another file owns are neither measured nor written — skipping the
+    # measurement is not just an optimisation here, it is what keeps the two
+    # tiers pinned to one set of trees. It also saves re-cloning the required
+    # corpus, whose largest member is 6,309 entries.
+    frozen = frozen_rows(taps)
+    failures: list[CorpusError] = []
     shas: dict[str, str] = {}
     counts: dict[str, int] = {}
-    failures: list[CorpusError] = []
+    if frozen:
+        print("  %d rows are owned by %s and are left alone"
+              % (len(frozen & {r for r, _s, _n in rows}), DEFAULT_TAPS.name))
     for repo, old_sha, _n in rows:
+        if repo in frozen:
+            continue
         try:
             try:
                 tap = registry.get(repo)
@@ -499,8 +549,10 @@ def _refresh(taps: Path, summary_path: str | None = None) -> int:
                  "" if sha == old_sha else "   MOVED"))
     if failures:
         return _report_failures(failures, len(rows))
-    taps.write_text(relock_text(taps.read_text(encoding="utf-8"), counts, shas),
-                    encoding="utf-8")
+    taps.write_text(
+        relock_text(taps.read_text(encoding="utf-8"), counts, shas,
+                    frozen=frozen),
+        encoding="utf-8")
     summary = refresh_summary(rows, shas, counts)
     print("\n" + summary)
     if summary_path:

boost_skill_cli-1.2.11/tests/eval/taps-scale.txt

@@ -0,0 +1,214 @@
+# GENERATED by scripts/build_scale_corpus.py — do not hand-edit.
+# Regenerate with that script; CI checks it with --check.
+#
+# The Tier 1b SCALE corpus: the required corpus (tests/eval/taps.txt)
+# plus distractors, so a metric difference between the two tiers isolates
+# the effect of the added candidates rather than confounding it with a
+# different set of targets. Every golden target lives in the required
+# rows, which are copied here verbatim — pins and counts included.
+#
+# Scheduled, never required. It exists because the required gate measures
+# 10,152 entries and a real install carries ~71,655, where all four floors
+# fail. It is A scale, not THE scale: hit@1 decays continuously with corpus
+# size and never plateaus, so no size here can be canonical.
+#
+# 165 distractor registries, 20,034 est items (the curated list's own estimate).
+# est_items under-reports by about 2.5x against a real install, so that
+# projects to roughly 50,860 actual entries — a projection, not a measurement.
+# The real counts are written in by `eval_corpus.py --refresh`, which is
+# also what pins these rows. Regenerating KEEPS any pin already here, so
+# --check verifies the selection, not the pins.
+#
+# Target: 20,000 est items. Selection: required rows first, then curated
+# registries largest-first WITHIN each type, round-robin across types —
+# straight largest-first lets the 341-strong skill tail crowd out the 26
+# rule registries, and a corpus that is 95% skills is not an install.
+
+# --- the required corpus, verbatim (holds every golden target) ---
+anthropics/skills                       b29e7cf65e5cb78a5ac33d582270551bc74a14eb    18
+0xfurai/claude-code-subagents           9236d10702cdbba37eaa34515f1e1dbff8452506   138
+NeoLabHQ/context-engineering-kit        555b95263ecf13d2ad9be14df676a1263d5a62b2    92
+Aaronontheweb/dotnet-cursor-rules       9be2d201482bdafca8c687359f0ef0a71895d7af    11
+ChrisWiles/claude-code-showcase         a95518f0cb67e86230119da40429169bc4c35a6f    14
+LessUp/awesome-cursorrules-zh           cd6a1f34f4f9eed7a01084751b9f6514eee1882d   470
+aliarghyani/vue-cursor-rules            92609798e192312ce16edb78aa5424a8caaa415b    14
+affaan-m/ECC                            e4e4163101f162881e628f300a9ca4e6a940bcea  1616
+BagelHole/DevOps-Security-Agent-Skills  0365f57a079b1332f95cf26e31dd2d5332a8399f   163
+composio-community/awesome-codex-skills 0930e1373789d2eda449039f7ac154b33031de89   880
+first-fluke/oh-my-agent                 3016e9df463f28f8c9c33f4e810a1901425a8bb0   136
+iktakahiro/python-fastapi-ddd-skill     aa498d4c81acae475e05528520009c275cbe554f     6
+langchain-ai/skills-benchmarks          064a5087fda3472a6b2883be7841441d038d2e2f    21
+minio/skills                            d54382989a5ccc5fcc7de2905f7454f944a28d76     3
+OneWave-AI/claude-skills                27f8cdcea225e627a73de89b9a3d477af9e249da   204
+quarkusio/quarkusdev-skills             b7c025b996bb4b9c3054740b242d1f368ae0eadd     5
+sickn33/antigravity-awesome-skills      d43065e483d9057e5c5dd50ca3647652ca7c0b43  6309
+tuanhaviet22/magento-skills             32d21015bd8eb46b8351fc87a8988ddca44de0f7     5
+anthropics/claude-agent-sdk-python      f8b9ec923982082a02c485924e0f60367949c3a1     6
+eclosion-labs/terraform-cursor-plugin   bcaad7033598c7bbb4efd73483b49962bd3398d9    41
+
+# --- distractors, curated registries (bare until the first --refresh pins them) ---
+sanjeed5/awesome-cursor-rules-mdc                 8fbf26908531c127a6076be0e55fbe17b57fb2d8  1121
+davila7/claude-code-templates                     b57c5c1e85a784aaf8e834a7e4997f3d56279542  1728
+mukul975/Anthropic-Cybersecurity-Skills           4c0b700ac5d280ba46695062077f0fe922ce3602   817
+pontusab/directories                              689fcbab801df547f1eea3e88660358be4f126ac     1
+loulanyue/awesome-claude-notes                    8481e67a3d17d5a2a0821901029862b526477b18  1479
+github/awesome-copilot                            318066d2213b510e89b500ed0d53506c54093ddc   664
+PatrickJS/awesome-cursorrules                     b044f956f021b6e8877f16781bcfc466a6a120e9   257
+davepoon/buildwithclaude                          a9fa86d0c6af0b12775211aff4188fdf6c3d9d0d  1125
+vibeeval/vibecosystem                             3b763b1fb288f57bfa3cce76ef18184b96461a78   486
+JhonMA82/awesome-clinerules                       dbd7a7c5e1aa5bff144f350801d49f86a21daab0   131
+Community-Access/accessibility-agents             161c60c7493ad657f371ad8f91253d33c3b12044   677
+j4flmao/agent-skills                              5da14236e30797df76bc1131a20c7ca43d770c46   576
+SchneiderSam/awesome-windsurfrules                0e77762fdfb6d703d5dd40a183d7fdb02103802e   129
+xu-xiang/everything-claude-code-zh                dfbf9467b90dfd29bffa842c4e0a6977112900e2   379
+Microck/ordinary-claude-skills                    1056d293d41a3a3b86518d8ab6ec0a79091ccedb  2148
+balqaasem/awesome-windsurfrules                   60797134e0d35338472adac269da851e474a9f8b   127
+qdhenry/Claude-Command-Suite                      e89b2f0b54f536a695ed7ae2e6e75e760b7a849e   358
+PramodDutta/qaskills                              287bbfb352a6384e95db04996d4d92cbe40669f0   426
+tugkanboz/awesome-cursorrules                     c2216ad56ceaef6a1455cbe85627c339d5148b42    20
+athola/claude-night-market                        90037391d2db6536f67a7ccc8dee7c6819f170b7   444
+thedaviddias/Front-End-Checklist                  30756a79b2f7d4363ac592710146c8e28fa9f1b5   390
+nedcodes-ok/cursorrules-collection                af98cf4915b88101bdd84253fb526ef08e352944   114
+rohitg00/awesome-claude-code-toolkit              ebdf1d596d2cde5c5cceb32177e8d1cf4829e7d9   438
+asgard-ai-platform/skills                         4e7f4f8e389847757a5a4236c2f1ed9813359179   314
+sparesparrow/cursor-rules                         53c530729aa2b5d37d3f7b7a065fa022db813626    64
+wshobson/agents                                   d6837ae274c2cd817acad3fb98f193a4390a4c3e   493
+alirezarezvani/claude-skills                      aa8d778811a557a2c28ccadda4cf3d0bd028a4cc  1209
+flyeric0212/cursor-rules                          f7a354d1185e065715168b08f6439845d5fb391c    42
+zebbern/claude-code-guide                         8428a63d016b2c2f92c54c2c6df3c46a0b9bfaf9    87
+rmyndharis/antigravity-skills                     3eff4af253b3a15e2ba6edf2c2b743b53fd81211   307
+survivorforge/cursor-rules                        ea0b7f5c702ad5336b11a994fd7ac13dad4f4f50    95
+Donchitos/Claude-Code-Game-Studios                984023ddac0d5e27624f2baacde6105e45de375f   171
+nWave-ai/nWave                                    1d0f13c79e9383c96a01b1a63e9a5bfd616c53d9   406
+jesseoue/cursor-rules                             fb3b82e120a5e4bd358ea807a24ee15ac1832054    45
+VoltAgent/awesome-claude-code-subagents           c9e51ec0b3d43f5dcdd0b558a6cd28ba6ada97c1   158
+pproenca/dot-skills                               cf93c57cac89d6fc3e4194686000411567f5caf3   211
+ivangrynenko/cursorrules                          8f652d24057ca37feae1c4a7185662f5589b0f5c    90
+Galaxy-Dawn/claude-scholar                        2f7766fd541a723d4ddc6230b3277f948d61b093   115
+shinpr/claude-code-workflows                      5f2cdc07397a5eef4feba48a144123e42c0d41b3   208
+Qwertic/cursorrules                               cd412562041fdd096bd706462c588a4ae1f69a9b   101
+agentlas-ai/Agentlas-OS                           e378c0addf67527b4ad3934dd3229b224dbc146e   329
+indranilbanerjee/digital-marketing-pro            fa4ccd0a4afc1b902ef8de8d297b180aa148d46a   205
+blefnk/awesome-cursor-rules                       eb2fdbc5ad0ae9aedeae09965e54ea6ad88dc715     0
+secondsky/claude-skills                           84802a4841cb632eee14175f5abe5276f4cb9596   303
+doccker/cc-use-exp                                448997909221b18dc45b3deced1c4c4f2039aa36   198
+matank001/cursor-security-rules                   ebbe0abd48ba08cadfaa3723ebfdf4914081e682    16
+davepoon/claude-code-subagents-collection         a9fa86d0c6af0b12775211aff4188fdf6c3d9d0d  1125
+MicrosoftDocs/Agent-Skills                        c579bb4b37e7969ffc8bc071ca0f53048c3bfe41   202
+DVC2/cursor_prompts                               39c160eb7285d825139675f802ec27a5a9102085    11
+Yeachan-Heo/oh-my-claudecode                      5aa678c6f7a769df84561d9486d8e9e30b68c3dc   103
+wanshuiyin/Auto-claude-code-research-in-sleep     0c65f8b34668c39f391b871ac61479eb64497c37   189
+quintonwall/cursorrules                           9c276601bbcc2c9750259bdec511ac04fdc5601a     0
+giuseppe-trisciuoglio/developer-kit               306f428f278d83722afdea44a7398dc46dab967f   220
+rshankras/claude-code-apple-skills                9ffb83138209057875698dd11c1720c657c47a92   183
+pekral/cursor-rules                               158fbfa8dc63c0302c2f21293d97a6e97881ce2b    85
+chusri/claude-code-agents                         167009899925732840059cdb2eca2c2c5aacd7f7    73
+finsilabs/awesome-ecommerce-skills                30a1fb674e41284e738608c059690c251699eb07   178
+BlueBirdBack/godot-cursorrules                    74ef10c6f96ed28a7e789dabdeb183c1086cf6d9     1
+nth5693/gemini-kit                                f3db206869f6f98b43c1207836a51f425527b763    73
+microsoft/skills                                  e20084b9d230c6f3b46ce36f011e6c3e50f79f8a   220
+digitalchild/cursor-best-practices                3296fb1ceb280b0fa801a270af1bce9b54dbcd45     5
+sangrokjung/claude-forge                          1642dc593d01b7af1b61c4aa594c93ba81b2d014    71
+nexscope-ai/eCommerce-Skills                      56f3288dd1ba3ae7cae43d369115a915229e510b   162
+wandb/agentic-support-bot-demo                    f9d4bb2394d3963eacccb3cdce3f5f4dfdb669aa     2
+Comfy-Org/comfy-claude-prompt-library             c1df6735799222b0362cc1753a0de94e5b9696ba    70
+claude-office-skills/skills                       9c4c7d5cd2813a8936bf2c9fdb174ea883b85a11   144
+ddd-crew/ai-ddd-prompts-and-rules                 95201874c6f4db08e84751bdb4a71f2a3aa9bcce     1
+composio-community/awesome-claude-plugins         e521f7ada8d89abea888e67b93b4dcfbb977041f    61
+mohitmishra786/low-level-dev-skills               bdc58472fa9f309ed1b3f7d985a0d8e9bd8f4608   142
+anthropics/claude-plugins-official                7458b5e539d2b1d4bff72a303250cab2f4744ef0    92
+jabrena/plinth                                    042f4ec1609d4aa0efecde21e716f34edbd2f9a3   160
+hoangsonww/Claude-Code-Agent-Monitor              36ffff7433fe3c1d77ae0b2cbaa50dc87f491b6b   135
+JetBrains/skills                                  e0f258b5cfed145015cb3e48da9a97947f7c4ed7   129
+dsifry/metaswarm                                  33d39f776f7fe29098dcf048955756a237e8cb40    58
+Owl-Listener/designer-skills                      20e34c4a587e5eb09fcdf8351fa97b3ad761b31e   139
+jezweb/claude-skills                              e875a6bfff809e5d42c584104031e36e1f014f18   121
+rampstackco/claude-skills                         0479242522549dfdb389bb9b7807ad4d6016ffb7   225
+wshobson/commands                                 27d3e77b1a844223721f6c983ddf261ac4441b89    15
+MengTo/Skills                                     22bacc4c4b5094001462d639df553a49a7642770   127
+glittercowboy/taches-cc-resources                 1757615b99ab789a72ff2d02e9f6112af2a15c04    54
+40RTY-ai/shopify-admin-skills                     6765cb4f436b225360a728e1eb9bd3d9ee674316   117
+aiwonglab/claude_code_agents                      c1a1a32eff57b5c047f15b4a40905423389b99a1    86
+guanyang/open-agent-hub                           71637f3d045fb84191322e9ff3134b0f0ff6a5b9   117
+trailofbits/skills                                04b241176fd9c10738a61df53d2c677c53e42990   117
+phuryn/pm-skills                                  18468a95b427e70e258b51389796367c6f684e7d   110
+cloudflare/agents                                 b2f1bd898fdbccf5c4815a48a7e8b8f8788c1468    47
+glebis/claude-skills                              46edb03cc915adbd78ee81e3406bc4480aefcaba   109
+pluginagentmarketplace/custom-plugin-nextjs       4f73e83c82adc3decdb6d09670867783396e7fe8    42
+browser-act/skills                                8f287271faa0c1df79a44578cb059102ff004da2   103
+syahiidkamil/Software-Engineer-AI-Agent-Atlas     fc0bf112e01ad4b19834880fdcbf812a22273167    41
+forcedotcom/sf-skills                             8a13a085744a7330397db4aa9fe6d2d1fc2c1867   196
+alirezarezvani/claude-code-skill-factory          ba18b31703542d9d7eda5f9ba94f0df65a59dddf    40
+Orchestra-Research/AI-Research-SKILLs             773a52944ba4747a18bd4ae9ade53fff041adcbc    98
+datopian/portaljs                                 88d0c1f869650b18627465762f5bb84f6700db01    39
+majiayu000/spellbook                              90095e175202dd3aa0a54ff1751d0a8d2dc52b51   105
+dl-ezo/claude-code-sub-agents                     532213dba7d4e6e9a15c95a025861c29dee9e459     1
+openakita/openakita                               5d5574dbae7d5cbc694d767208509613e0822449   177
+humanlayer/humanlayer                             99abe673498cf8bdcd5f989aebe9406a27185b3b    34
+Leooooooow/Awesome-eCommerce-Skills               19a348e4f90fab4930d20364d1ac78252c6fdf4b    97
+anthropics/claude-code                            354757e5b2d9aa1ebb62e5d05ecd384f0e11c0f7    43
+elementalsouls/Claude-BugHunter                   60cad9aaefc197f569ba214cdba24b167edd3ae0    98
+lst97/claude-code-sub-agents                      96f5a506793d1c2e4a66c3ec3ce63c2cd2667728    37
+full-stack-skills/t2ui-skills                     f22b8c77017dfc42b26ad35a2c54f9bc722710bb    97
+darrenhinde/OpenAgentsControl                     37ca233fa5597a5abb90cba73165deafffe0344f   115
+google/skills                                     cdca572d24dbc6fa5b7bfd1af57585209556c849   112
+dotnet/skills                                     76c8ac0b473a1493c757094a2a7369f1f53ede34   132
+lebsral/DSPy-Programming-not-prompting-LMs-skills ededb2fbcb36b7a4eb8ebd3d20e67963fda418f7    96
+danielrosehill/Claude-Slash-Commands              cf3644b4890ddfab833458055cad926b24b10899   401
+SpaceZephyr/myskill                               fa7105abbaf10c52da989990f248316c5e8ab4b7    95
+kasperjunge/agent-resources-legacy                aefe9b22e44579dc0481f9a9b7be87aa3a050a9a    15
+ihlamury/design-skills                            126714ec5df13a2c97ce1b3975e5a51d2592d967    87
+centminmod/my-claude-code-setup                   823d721d964c751e54c690f848f776fef9813b2c    34
+dpearson2699/swift-ios-skills                     8d90fd121a263355a4fb44fd082af1416a5c1c2a    86
+pluginagentmarketplace/custom-plugin-kotlin       cc703d88715618fef4d7196f3bb68b86a9717873    28
+inference-sh/skills                               becc25649700d5457772a00e5143e28ccf9e5afa    86
+hnaymyh123-henry/claude-dev-skill                 3e87db0c71ff51ad19c932a6849777e66398f556    26
+product-on-purpose/pm-skills                      e8518d47cd00831b0fc38bd70f83af8566b0186f   100
+klovaaxel/web-a11y-agent-skills                   15fa84624b15ec8823f88c176ce11eb9c0f24c29    26
+tech-leads-club/agent-skills                      fe318be656b315d5b6f45cf7ea23946b2d0241b0    88
+brennercruvinel/CCPlugins                         b02d67e33091abff7cef3c98465fc1fa5f96ba46    23
+zhaoxuya520/reverse-skill                         ea582f30d53e4d616881df06a8e0f7e9f661ea21    85
+vijaythecoder/awesome-claude-agents               2050f3c60fcfea497f7b6b3ec6566cc316367a7e    33
+ninehills/skills                                  f3e82a7e2bfbed54fc2b4a715a1986f5f467e827    88
+codenamev/ai-software-architect                   69d5b6962acc4e91a026bd325b44d6174c06824e    20
+syncfusion/maui-ui-components-skills              98ef80228249fccd30f7b18651198378af0ceaf0    77
+steipete/agent-rules                              42993e48c165d8dfe44baacef7daee1edb38f0c6    32
+ancoleman/ai-design-components                    76551b7b19ebc667764ec75da14990d0aef8b6e5    76
+talknerdytome-labs/claude-agents                  2cbb09f4b254756d218fe15fea4ac2d0fdac12e5     2
+deanpeters/Product-Manager-Skills                 a03af68414bb0b924746c97bddf9a5057d017af7    83
+anthropics/claude-cookbooks                       35f2eec7e44897c537e44441b7dff2f0ecbfb804    21
+jamditis/claude-skills-journalism                 deea6d5590efc608f8a83efcd9c3982ed7b35990    90
+glapsfun/cnative-skills                           15365d4d203d93d0a22132eefb760bd9a00b849d    35
+Houseofmvps/ultraship                             ed232cba00040a3a8294aff08d14a0053cb8a0ae    74
+iannuttall/claude-agents                          f7df2c3e7395d163ad52d0793bac8fa7ce0d776a     7
+jame581/GodotPrompter                             eae755a1f3719076d52f50ab76f21993ebb9682b    74
+ducpm2303/claude-java-plugins                     006a789364c3350c0e691f1f1e8c4fe5859cdcab    37
+BuilderIO/agent-native                            4152bd69f5e8037ca501b93871d232b8849168da   629
+piomin/claude-ai-spring-boot                      d87e7a38588a0a945ae2c11a251954897692330e    11
+SamurAIGPT/Generative-Media-Skills                3b62f7870496a10ebab42221e5e3226ad0ef8a9e    73
+anthropics/claude-code-action                     459ad358ae43fea66bfefd0a1f8d840b4b9791fb     8
+tradermonty/claude-trading-skills                 769a6c88b16ccdc3239a14fcbaf9ef2c44d183a8   125
+anthropics/financial-services                     38652224c10610fa52eee2acee3ac712dcff01f2   184
+LambdaTest/agent-skills                           0491a3a29aa18558d2c3c64ff09367adb976c56f    72
+hikarubw/claude-commands                          ce26a4f5ae4b3eb9c3781167931bb74ddb935c43     7
+anbeime/skill                                     e768930e260334aaab2e666869b9122a1b5bfeea    76
+anthropics/claude-agent-sdk-demos                 826b268506a5f3707623c9e6140b200befcbebae    12
+internet-court/internet-court-skill               251d269e9e17a4554616b34fc78f5858ee9eef1d    93
+comet-ml/opik-claude-code-plugin                  c351661fd470b17c147bca5b664f450864db89ad     5
+TheGoat395/Codex-Skills                           dbd0e70e99671af0940c7b8a85208b2f6696bc7f    71
+docker/claude-plugins                             278e8ebe3d46e17b771323ea6a6f281bded10e08     3
+daymade/claude-code-skills                        f5f4c41e716aa34eab03f06d5128cd1a3a7dca90    93
+langchain-ai/deepagents                           41395c586d9743550c27073260539724a4bfedd3    35
+JasonColapietro/suede-creator-skills              d97dd485737839ff776bd4495f1ea31b636130b4    76
+zenml-io/skills                                   e8534cade92e1c0ce730e421de830509b04be6d2    16
+bergside/awesome-design-skills                    f631a09b4fcc0166f2e2c1a8c81906ef680c57e8    67
+DavidROliverBA/Daves-Claude-Code-Skills           396429a7668dfb2440ac03066b83abe54143421a     4
+air-gapped/skills                                 74ea1cf60aaf55ab5f2aed6fad1a168dfea39c17    76
+anthropics/claude-agent-sdk-typescript            a616205d6cb7c2f5907120f660f6391310918369     1
+jeffallan/claude-skills                           882ef55e377dbf9a4dbe496bb41ac6ccd0e555cf    80
+anthropics/claude-code-security-review            0c6a49f1fa56a1d472575da86a94dbc1edb78eda     1
+spencerpauly/awesome-cursor-skills                99cd2655788456cc1c685944dcf8c2de82c1ded4    65
+anthropics/cwc-long-running-agents                ad107a974bced5244f74dd283dbf2bfd3baee3a1     1
+chaterm/terminal-skills                           464c2954287ad0c0b9addb1ebfbb2150ddc0de24    63
+jeremylongshore/claude-code-plugins-plus-skills   109179f92cf7f01b95ad2f88fd15956713631fc2  6430
+wondelai/skills                                   6bac1534f9f256a56fc2b4dd0e70b9a692758966   188