Agent skill

Hns Lsel Applier

by modu-ai in modu-ai/moai-adk

Local Self-Evolution Loop (LSEL) APPLY engine — the playback-only consumer of approved decision.json records that drives .moai/hooks/lsel-apply.sh for the GOOS-local PROPOSE→APPLY seam closure…

Apache-2.0Auto-check: notesDevelopment

Install Hns Lsel Applier

skills CLI
$ npx skills add modu-ai/moai-adk --skill hns-lsel-applier -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install modu-ai/moai-adk hns-lsel-applier --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/modu-ai/moai-adk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/hns-lsel-applier .claude/skills/hns-lsel-applier && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hns-lsel-applier
GitHub stars
1.2k
Token cost
~3k tokens
SKILL.md length
1,228 words
Files
5
Skills in repo
48
Repo updated
First seen
Licence
Apache-2.0

At a glance

Local Self-Evolution Loop (LSEL) APPLY engine — the playback-only consumer of approved decision.json records that drives .moai/hooks/lsel-apply.sh for the GOOS-local PROPOSE→APPLY seam closure…

  • Works in 5 steps: Frozen-allowlist hard-reject… → Execution-meta forced-gate (REQ-LSEL-002… → Apply the diff.patch via git apply… → …
  • Tasks that involve Commit messages
  • SKILL.md covers What this skill does, The APPLY pipeline, The model-mediated layer (you,… and What this skill does NOT do, plus 3 more sections
  • Runs Shell scripts from its folder; calls git

What it does

Hns Lsel Applier is an agent skill from modu-ai/moai-adk. Local Self-Evolution Loop (LSEL) APPLY engine — the playback-only consumer of approved decision.json records that drives .moai/hooks/lsel-apply.sh for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001 M3). Reads an approved decision.json, validates the target against the frozen allowlist (.claude/lsel/frozen-allowlist.json), mechanically refuses execution-meta targets lacking a synchronous-approval marker, applies the referenced diff.patch, appends an apply-ledger.jsonl row, and commits one…

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `apply_test.sh`, `rollback_rehearsal_test.sh` and `verify.sh`).

It sits in Development, covering Commit messages. The repository describes itself as: Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Single Go binary, 16… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Commit messages

Example prompts

  • “/hns-lsel-applier”

Requirements

  • A Bash shell
  • Pre-approved tools (allowed-tools): Read, Grep, Glob, Bash

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Frozen-allowlist hard-reject (REQ-LSEL-001 / AC-LSEL-001). The target path in
  2. Execution-meta forced-gate (REQ-LSEL-002 / AC-LSEL-005 D3 self-amending-
  3. Apply the diff.patch via git apply (playback of an already-approved decision).
  4. Append the apply-ledger row to .moai/state/lsel/apply-ledger.jsonl
  5. Commit the staged change as ONE feat(lsel-): ... Conventional

What it can do on your machine

Read from SKILL.md and the folder at commit 2aab5f7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep
    • Glob
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hns Lsel Applier loads about 3k tokens when it runs. Until then it costs about 189 tokens; SKILL.md has 1,228 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~189
When it runs · the whole SKILL.md, loaded when a task matches
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Grep, Glob, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from modu-ai/moai-adk at commit 2aab5f7, republished under its Apache-2.0 licence (© modu-ai). 1,228 words, ~3,022 tokens.

Download SKILL.mdSave it as .claude/skills/hns-lsel-applier/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
hns-lsel-applier
description
Local Self-Evolution Loop (LSEL) APPLY engine — the playback-only consumer of approved decision.json records that drives `.moai/hooks/lsel-apply.sh` for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001 M3). Reads an approved decision.json, validates the target against the frozen allowlist (.claude/lsel/frozen-allowlist.json), mechanically refuses execution-meta targets lacking a synchronous-approval marker, applies the referenced diff.patch, appends an apply-ledger.jsonl row, and commits one lsel-<proposal-id>-tagged Conventional Commit on the feature branch. M3 scope: APPLY bypass closure only (the frozen Go applier stays frozen — its write-flag at internal/harness/applier.go:22 stays false; REQ-LSEL-003).
allowed-tools
Read, Grep, Glob, Bash
user-invocable
false
metadata.version
0.1.0
metadata.category
harness
metadata.status
active
metadata.updated
2026-08-04
metadata.tags
lsel,self-evolution,apply,harness,dogfood

hns-lsel-applier — LSEL APPLY engine

Namespace: hns-lsel-* is user-owned dogfood (CLAUDE.local.md §24). This skill is NOT mirrored into internal/template/templates/ — it lives only in this repo. Graduation to moai-lsel-* + 16-language distribution is a separate SPEC (out of scope per spec.md §G).

Token discipline. This body deliberately avoids the literal identifier of the frozen Go applier's write-flag and the literal name of the orchestrator-only user-question channel. Both are referenced by location and role (e.g. "the write-flag at internal/harness/applier.go:22", "the orchestrator's synchronous user gate") so the REQ-LSEL-003 invariant-grep and the E4 subagent-boundary grep over LSEL surfaces read zero literal matches. The invariants themselves are stated in plain English.

What this skill does

The LSEL loop's PROPOSE→APPLY seam was dead in production: Applier.Apply never ran (manifest.jsonl absent), CuratorDispatch had 0 production callers, and the frozen Go applier's write-flag at internal/harness/applier.go:22 (kept false) is the apply dead-switch (REQ-LSEL-003 — M3 keeps it false by BYPASS, never unfreeze). The M3 closure routes APPLY through a parallel user-owned applier that writes only to the six evolvable surfaces (spec.md §B.3), while the frozen Go applier stays byte-for-byte frozen. Design SSOT: .moai/reports/moai-local-self-evolution-design-20260804.html §4 ("동결된 Go applier를 우회하는 병렬 사용자 소유 applier를 세운다" — build a parallel user-owned applier that bypasses the frozen Go one) + §7 (the two-round critique moved the allowlist OUT of the evolvable skill files into a frozen meta file, and added execution-meta files to the forced-gate set).

The APPLY engine is the playback hook .moai/hooks/lsel-apply.sh plus this skill's model-mediated judgment (target validation nuance, approval-marker provenance, blast- radius reasoning the mechanical hook cannot see). The hook is the load-bearing safety floor; this skill is the consumer-facing surface that decides WHICH approved decision to feed it next and how to interpret refusal.

The APPLY pipeline

lsel-apply.sh <decision.json> performs five steps. Steps 1-2 are the safety floor; steps 3-5 are the playback.

  1. Frozen-allowlist hard-reject (REQ-LSEL-001 / AC-LSEL-001). The target path in decision.json is matched against the frozen_patterns regex list in .claude/lsel/frozen-allowlist.json. A match → REFUSE: a row is appended to .moai/logs/lsel-reject.log naming the rejected path and category frozen-path, NO file is written, and the hook exits 2.
  2. Execution-meta forced-gate (REQ-LSEL-002 / AC-LSEL-005 D3 self-amending- handcuffs). If the target matches one of the four execution_meta categories — (i) the frozen allowlist meta file itself, (ii) an applier/curator skill body (hns-lsel-applier/, hns-lsel-curator/), (iii) the apply hook (.moai/hooks/lsel-*.sh), (iv) the settings.local.json hook-registration subblock — the hook checks decision.json for a synchronous-approval marker (a synchronous_approval object with decision: "approved", produced by the orchestrator's synchronous user gate). No marker → REFUSE: reject-log row with category execution-meta, exit 3, no write. With marker → proceeds (the refusal is keyed on the absent marker, NOT on the category match alone). The refusal semantics mirror the M2 csa_refusal_test.sh fixture exactly.
  3. Apply the diff.patch via git apply (playback of an already-approved decision). Only the paths declared in the patch are staged — never git add -A (working-tree hygiene).
  4. Append the apply-ledger row to .moai/state/lsel/apply-ledger.jsonl: {proposal_id, target_surface, ts, result:"applied", commit_sha, category}. This is the manifest the frozen Go applier never produced, finally real in user-owned space.
  5. Commit the staged change as ONE feat(lsel-<proposal-id>): ... Conventional Commit on the current (feature) branch (REQ-LSEL-004). The ledger row's commit_sha is backfilled from the commit's short SHA.

A no-arg invocation is a clean no-op (exit 0) so an empty approved-queue does not derail a loop pass.

The model-mediated layer (you, when invoked)

When this skill is invoked to drive an APPLY pass, your job on top of the mechanical hook is:

  • Read the proposal's proposal.md + self-critique.md at .moai/state/lsel/proposals/<id>/. A proposal with status: blocked (any UNRESOLVED self-critique objection) MUST NOT be fed to the hook — return a blocker report instead.
  • Confirm the approval marker's provenance. The synchronous_approval object must carry a real orchestrator-produced approval artifact (the synchronous user-question channel the orchestrator owns per askuser-protocol.md). A marker the loop fabricated for itself is the self-amending-handcuffs failure mode (REQ-LSEL-002); the hook's mechanical check is the floor, your provenance judgment is the ceiling. This skill is a subagent mechanism and NEVER invokes the orchestrator-only user-question channel; return a blocker report and let the orchestrator run the gate.
  • Re-verify the frozen-allowlist invariant by grepping the write-flag at internal/harness/applier.go:22 — it MUST stay false. If M3's bypass ever drifts toward unfreezing the Go applier, return a blocker (AP-LSEL-002).
Show full SKILL.md (527 more words)Show less

What this skill does NOT do

  • No unfreezing of the Go applier — the write-flag at internal/harness/applier.go:22 stays false (REQ-LSEL-003). The bypass is parallel and user-owned; the frozen applier is reference-only.
  • No edits to frozen doctrine — internal/template/templates/**, .claude/rules/moai/**, AGENTS.md, retained agents, moai-* skills, the frozen Go applier / curator_dispatch.go, and .moai/config/sections/** are byte-for-byte untouched. The allowlist hard-rejects them (step 1).
  • No new-apply / self-approve / allowlist-amend primitive in lsel-apply.sh (REQ-LSEL-008). The hook only consumes already-approved decisions; it does not author proposals or bless them. The M4 verify.sh runs only AFTER an apply has committed — it does not create a new apply; it never self-approves.
  • No user-question invocation — subagent boundary (askuser-protocol.md). Return a blocker report; the orchestrator runs the synchronous gate.

VERIFY stage (M4 — REQ-LSEL-013 / AC-LSEL-015)

After an apply commits a proposal, VERIFY proves the apply was safe. VERIFY has two layers — both MANDATORY:

(a) Mechanical layer — verify.sh (bash-testable)

verify.sh --proposal-dir <p> --repo-root <r> [--timeout SECS] [--feedback-file <f>] runs the proposal's frontmatter verify_command with a timeout-retry-once policy and auto-reverts on a second failure:

  • 2-attempt policy. Attempt 1 runs. On SUCCESS → verified:true, stop. On TIMEOUT-class failure → attempt 2 (flaky tolerance — report §10 P3: "retry once on timeout so a correct proposal isn't flipped by noise"). On NON-TIMEOUT-FAIL → attempt 2 (allows the "second non-timeout failure" of AC-LSEL-015 clause 3 to materialize before revert fires).
  • Attempt 2: SUCCESS → verified:true. Any failure (timeout OR non-timeout) → verified:false + auto git revert lsel-<proposal-id> + the proposal's feedback_*.md is marked verified: false.
  • The outcome is appended to the apply ledger as a {"stage":"verify","verified":true|false,...} row — the load-bearing signal.
(b) MANDATORY /moai gate superset (model-mediated)

/moai gate (lint+format+type+test) is MANDATORY after every apply — it is NOT optional. A bash hook cannot invoke a Claude Code slash command directly, so the gate runs MODEL-SIDE: when this skill drives an APPLY pass, the orchestrator/model runs /moai gate after the mechanical apply + verify. The proposer-authored verify_command alone is circular (report §11 mustFix B#6 / AP-LSEL-004): a proposer can author a verify_command that its own change satisfies. /moai gate is the independent check — lint, format, type-check, and the test suite exercise surfaces the proposal never touched. Treat a mechanical verify_command PASS without a green /moai gate as an unverified apply.

Model-mediated layer (you, when invoked)
  • After lsel-apply.sh commits and verify.sh reports, run /moai gate (the MANDATORY superset). If the gate fails, the apply is unverified even if verify.sh reported verified:true — treat it as a VERIFY failure and revert.
  • A revert (whether auto-fired by verify.sh or gate-driven) MUST be surfaced to the orchestrator as a blocker report — the orchestrator, not this skill, confirms a revert with the user. Never run /moai gate's user-facing surface from inside this subagent mechanism; return a blocker report.
Verification (run before declaring an APPLY+VERIFY pass complete)
bash
# M4 VERIFY characterization test (AC-LSEL-015) — hermetic temp repo:
.claude/skills/hns-lsel-applier/verify_test.sh

# the verify ledger row carries the outcome:
grep '"stage":"verify"' .moai/state/lsel/apply-ledger.jsonl

Verification (run before declaring an APPLY pass complete)

bash
# 1. APPLY characterization test (AC-001/002/005/008/013) — hermetic temp repo:
.claude/skills/hns-lsel-applier/apply_test.sh

# 2. Rollback-rehearsal SHIP GATE (AC-014):
.claude/skills/hns-lsel-applier/rollback_rehearsal_test.sh

# 3. REQ-LSEL-003 frozen-flag re-verify (post-apply). The frozen Go applier's
#    write-flag at internal/harness/applier.go:22 MUST read `false`, and no LSEL
#    surface (skills/hooks/state/allowlist) references that identifier as mutable.
#    (The literal identifier is intentionally not written here; find it at line 22
#    of the frozen file and grep LSEL surfaces for it — expect zero hits.)
sed -n '22p' internal/harness/applier.go   # MUST show the `= false` write-flag line

# 4. The apply ledger carries the new row:
tail -1 .moai/state/lsel/apply-ledger.jsonl

Cross-references

  • SPEC: .moai/specs/SPEC-LSEL-LOCAL-EVOLUTION-001/{spec,plan,acceptance,progress}.md
  • Design report (SSOT): .moai/reports/moai-local-self-evolution-design-20260804.html §4 (user-owned parallel applier), §7 (allowlist relocation + execution-meta forced gate), §10 P3, §11 mustFix A#1/A#5/A#8.
  • Frozen applier (reference only): internal/harness/applier.go:22 (the frozen write-flag), internal/harness/curator_dispatch.go.
  • Curator (PROPOSE stage, M2): .claude/skills/hns-lsel-curator/SKILL.md (CSA forced-gate doctrine + the Tier-4 DEAD finding).
  • CSA refusal fixture: .claude/skills/hns-lsel-curator/csa_refusal_test.sh (the refusal rule this hook enforces mechanically).
  • Namespace guard: internal/template/split_namespace_test.go, internal/template/internal_content_leak_test.go (must NOT flag a hns-lsel-applier leak — this skill is dogfood, never templated).

© modu-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files in .claude/skills/hns-lsel-applier of modu-ai/moai-adk.

  • SKILL.md
  • apply_test.sh
  • rollback_rehearsal_test.sh
  • verify.sh
  • verify_test.sh

Open the folder on GitHubat commit 2aab5f7

Compare with similar skills

Hns Lsel Applier next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hns Lsel Applier compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hns Lsel Applier this skillmodu-ai/moai-adk1.2k—~3kAutomated safety check: NotesApache-2.0
Contextual Commit Messagesyamadashy/repomix29k1 repos~2.7kAutomated safety check: PassMIT
React Router Release Notes Prepremix-run/react-router57k—~1.1kAutomated safety check: PassMIT
Caveman Commitvishiri/fantasia-archive40913 repos~642Automated safety check: PassGPL-3.0
PR Finalize Reviewmicrosoft/garnet12k—~3.1kAutomated safety check: PassMIT
ToolJet Multi-Repo CommitToolJet/ToolJet41k—~1.3kAutomated safety check: PassAGPL-3.0

Similar skills

  • Writes Conventional Commits whose bodies carry action lines recording the intent, decisions and constraints behind a change, not only what changed.

    29k GitHub starsUsed in 1 repo~2.7k tokens
    DevelopmentAuto-check passed
  • React Router Release Notes Prep

    remix-run/react-router

    Polishes pending React Router change files before the versioning scripts run, and decides whether a long-form What's Changed section is warranted.

    57k GitHub stars~1.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Caveman Commit

    vishiri/fantasia-archive

    Ultra-compressed commit message generator. An agent skill from vishiri/fantasia-archive.

    409 GitHub starsUsed in 13 repos~642 tokens
    DevelopmentAuto-check passed
  • PR Finalize Review

    microsoft/garnet

    Official

    Checks that a pull request's title and description match its implementation and reviews the code for Garnet best practices, reporting findings without posting them.

    12k GitHub stars~3.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Commits changes across ToolJet's root repo and its server/ee and frontend/ee submodules, writing messages from the diffs and updating submodule pointers in order.

    41k GitHub stars~1.3k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Git Workflow and Versioning

    addyosmani/agent-skills

    Sets git habits for every change: short-lived branches, atomic commits with descriptive messages, clean pull requests, plus versioning, tagging and changelogs for releases.

    105k GitHub starsUsed in 2 repos~3.5k tokens
    DevelopmentAuto-check: notes

More from modu-ai/moai-adk

All 48 skills in this repo
  • Builds hand-editable SVG diagrams from computed layout coordinates, lints the source and renders a 2x PNG, with rules for when mermaid is the better choice.

    1.2k GitHub stars~5.2k tokensUpdated yesterday
    Auto-check: notes
  • MoAI Foundation Core

    modu-ai/moai-adk

    Reference for MoAI-ADK's core development principles: TRUST 5 quality gates, SPEC-first domain-driven workflow, agent delegation and token budgeting.

    1.2k GitHub stars~5k tokensUpdated yesterday
    Auto-check passed
  • MoAI SPEC Workflow

    modu-ai/moai-adk

    Manages SPEC documents for MoAI-ADK development, with GEARS or EARS requirement notation, acceptance criteria and a link into the Plan-Run-Sync workflow.

    1.2k GitHub stars~5.1k tokensUpdated yesterday
    Auto-check passed
  • MoAI TDD Workflow

    modu-ai/moai-adk

    Drives test-first development through the RED, GREEN, REFACTOR cycle, with a config switch that selects between TDD and a DDD workflow for existing code.

    1.2k GitHub stars~3.1k tokensUpdated yesterday
    Auto-check passed
  • MoAI Worktree Management

    modu-ai/moai-adk

    Gives each SPEC its own Git worktree with a registry of active workspaces, base-branch sync and cleanup of merged ones, inside the MoAI-ADK workflow.

    1.2k GitHub stars~3.9k tokensUpdated yesterday
    Auto-check passed
  • Watches a pull request's CI checks after creation, separates required from auxiliary failures, applies limited safe fixes and escalates anything semantic to you.

    1.2k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check: notes

Categories

Questions about Hns Lsel Applier

What does Hns Lsel Applier do?

Local Self-Evolution Loop (LSEL) APPLY engine — the playback-only consumer of approved decision.json records that drives .moai/hooks/lsel-apply.sh for the GOOS-local PROPOSE→APPLY seam closure…. Hns Lsel Applier is an agent skill from modu-ai/moai-adk.sh for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001 M3).

When should I use Hns Lsel Applier?

Hns Lsel Applier fits situations like: tasks that involve Commit messages.

How do I install Hns Lsel Applier in Claude Code?

Run `npx skills add modu-ai/moai-adk --skill hns-lsel-applier -a claude-code`. Or copy the skill folder (.claude/skills/hns-lsel-applier in modu-ai/moai-adk) into .claude/skills/hns-lsel-applier in your project. Claude Code loads it when a task matches its description.

How do I install Hns Lsel Applier in Codex?

Run `npx skills add modu-ai/moai-adk --skill hns-lsel-applier -a codex`. Or copy the skill folder (.claude/skills/hns-lsel-applier in modu-ai/moai-adk) into .agents/skills/hns-lsel-applier in your project. Codex loads it when a task matches its description.

Can I use Hns Lsel Applier in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add modu-ai/moai-adk --skill hns-lsel-applier -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hns-lsel-applier, .gemini/skills/hns-lsel-applier, .github/skills/hns-lsel-applier and .opencode/skills/hns-lsel-applier in your project.

What does Hns Lsel Applier need to run?

Going by SKILL.md and its folder, Hns Lsel Applier needs a shell for the scripts in its folder and the command-line tools its instructions call (git). Our summary lists: A Bash shell. Its frontmatter pre-approves these tools: Read, Grep, Glob, Bash.

Does Hns Lsel Applier access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Hns Lsel Applier safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Hns Lsel Applier use?

Hns Lsel Applier is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hns Lsel Applier use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Hns Lsel Applier?

Skills that share tags, products or a category with Hns Lsel Applier: Contextual Commit Messages (yamadashy/repomix, 29k stars), React Router Release Notes Prep (remix-run/react-router, 57k stars), Caveman Commit (vishiri/fantasia-archive, 409 stars) and PR Finalize Review (microsoft/garnet, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hns Lsel Applier?

modu-ai (a GitHub organization) maintains it in modu-ai/moai-adk, which has 1,230 GitHub stars. The repository holds 48 skills in this directory. The repository was last updated on October 9, 2026.

Source: modu-ai/moai-adk on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.