Earnings Analysis
Wind-Alice/AliceMarket
Create professional equity research earnings update reports (8-12 pages, 3,000-5,000 words) analyzing quarterly results for companies already under coverage.
Analyze earnings releases, filings, transcripts, guidance, peer comparisons, market reaction, and thesis impact for a company reporting event.
$ npx skills add byteseek/Mira --skill earnings-report-analysis -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install byteseek/Mira earnings-report-analysis --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/byteseek/Mira.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/earnings-report-analysis .claude/skills/earnings-report-analysis && rm -rf skills-srcUse ~/.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/
Install the "earnings-report-analysis" agent skill from https://github.com/byteseek/Mira/tree/main/skills/earnings-report-analysis into .claude/skills/earnings-report-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "earnings-report-analysis", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/byteseek/Mira/tree/main/skills/earnings-report-analysisType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add byteseek/Mira --skill earnings-report-analysis -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install byteseek/Mira earnings-report-analysis --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/byteseek/Mira.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/earnings-report-analysis .agents/skills/earnings-report-analysis && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "earnings-report-analysis" agent skill from https://github.com/byteseek/Mira/tree/main/skills/earnings-report-analysis into .agents/skills/earnings-report-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "earnings-report-analysis", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add byteseek/Mira --skill earnings-report-analysis -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install byteseek/Mira earnings-report-analysis --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/byteseek/Mira.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/earnings-report-analysis .cursor/skills/earnings-report-analysis && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "earnings-report-analysis" agent skill from https://github.com/byteseek/Mira/tree/main/skills/earnings-report-analysis into .cursor/skills/earnings-report-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "earnings-report-analysis", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/byteseek/Mira.git --path skills/earnings-report-analysis--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add byteseek/Mira --skill earnings-report-analysis -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install byteseek/Mira earnings-report-analysis --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/byteseek/Mira.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/earnings-report-analysis .gemini/skills/earnings-report-analysis && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "earnings-report-analysis" agent skill from https://github.com/byteseek/Mira/tree/main/skills/earnings-report-analysis into .gemini/skills/earnings-report-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "earnings-report-analysis", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install byteseek/Mira earnings-report-analysisInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add byteseek/Mira --skill earnings-report-analysis -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/byteseek/Mira.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/earnings-report-analysis .github/skills/earnings-report-analysis && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "earnings-report-analysis" agent skill from https://github.com/byteseek/Mira/tree/main/skills/earnings-report-analysis into .github/skills/earnings-report-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "earnings-report-analysis", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add byteseek/Mira --skill earnings-report-analysis -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install byteseek/Mira earnings-report-analysis --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/byteseek/Mira.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/earnings-report-analysis .opencode/skills/earnings-report-analysis && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "earnings-report-analysis" agent skill from https://github.com/byteseek/Mira/tree/main/skills/earnings-report-analysis into .opencode/skills/earnings-report-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "earnings-report-analysis", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
earnings-report-analysisAnalyze earnings releases, filings, transcripts, guidance, peer comparisons, market reaction, and thesis impact for a company reporting event.
Earnings Report Analysis is an agent skill from byteseek/Mira. Analyze earnings releases, filings, transcripts, guidance, peer comparisons, market reaction, and thesis impact for a company reporting event.
Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Business, Finance & HR, covering Essays and academic help and Financial analysis. The repository describes itself as: Agent-native investment research workspace for evidence-tracked, refreshable investment theses across equities, earnings, macro, and portfolio review. The licence is Apache-2.0.
9 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit adddce7. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Earnings Report Analysis loads about 2.6k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 774 words of instructions outside code blocks.
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.
The automated check found no risky patterns in SKILL.md.
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.
The full file from byteseek/Mira at commit adddce7, republished under its Apache-2.0 licence (© byteseek). 774 words, ~2,607 tokens.
.claude/skills/earnings-report-analysis/SKILL.md (or your agent's skills folder).这个 skill 用于对单家公司的一份季报、半年报或年报做结构化分析。它服务于 research package,但输出重点从完整投资 memo 收窄到财报质量、经营变化和预期差。
默认时间跨度是 near_term_execution 到 medium_term_revision。只有当本期财报证据触及长期驱动变量,并且被订单、客户、产能、现金流、同行或产业链证据支持时,才允许把结论升级为 long_term_thesis 或 regime_transition。
L1 财报、公告、业绩新闻稿或监管文件L1 或 L4 业绩会 transcript / prepared remarks / Q&A 摘要L5 价格、估值、市场预期或分析师一致预期L1 至少一家核心竞争对手的同期财报、公告或业绩新闻稿L6 派生计算表在只摘录披露数字时可选;如果输出同比、环比、margin bridge、implied guidance、peer relative quality、valuation delta 或任何影响 thesis/actionability 的数量判断,则必须生成 calculation ledger,并指向上游 L1 到 L5财报分析默认使用 sec_supplement,而不是完整拆 filing。
使用 sec_supplement 的场景:
升级到 sec_filing_deep_dive 的场景:
如果 10-Q/10-K 尚未发布,必须写 source-gap refresh,不得把 release 中缺失的现金流、债务细节或风险因素当作不存在。
默认输出到 templates/earnings-analysis-package/ 结构:
earnings-analysis.mdevidence-log.csvfinancial-snapshot.csvpeer-comparison.csv如果财报事件用于维护已有 thesis,还必须输出或更新 Thesis System 事件对象:
event-delta.md如果该财报足以改变投资结论,再同步更新标准 research package:
investment-memo.mdcase-notes.mdevidence-log.csv先用经营语言描述本期财报,而不是直接进入会计数字:
核心业务图谱必须回答:这家公司本期到底是“卖得更贵了”、“卖得更多了”,还是只是会计口径或组合变化。
把增长拆成两个优先维度:
pricing:是否具备定价权、提价权、议价权或供需主动权volume:供需上是否可以扩大业务量,且扩量是短期还是持久pricing 判断要覆盖:
volume 判断要覆盖:
每个增长驱动必须标记为 price-driven、volume-driven、mix-driven、cost-driven、accounting-driven 或 one-off,并标记证据强度:high、medium、low 或 source_gap。
定价、放量和持久性不能只引用管理层口径。必须把证据分层,并记录反证。
| dimension | high evidence | medium evidence | weak evidence / not enough alone | common counter-evidence |
|---|---|---|---|---|
| pricing | realized price / ASP / net price 上升;折扣收窄;续约或新合同提价被接受;毛利改善可排除成本、汇率、补贴或一次性项目 | product mix 向高 ASP / 高毛利迁移;交期拉长、配额销售或供给紧张;同行同步提价或折扣收窄 | 管理层只说 pricing strong;收入增长但没有 ASP、折扣或毛利桥;毛利改善主要来自成本下降或良率改善 | ASP 下滑;促销或折扣扩大;gross-to-net 恶化;客户重谈合同;同行降价 |
| volume | 出货、销量、活跃客户、订单、RPO/backlog、book-to-bill 或 usage 明确增长;产能、供应链和客户验收支持交付 | 指引隐含放量;产能扩张按期;新客户、新地区或新平台开始贡献;渠道 sell-through 改善 | 低基数同比高增;一次性补库存;提前拉货;只给 TAM 或 pipeline 叙事 | backlog / RPO 环比下降;订单取消或延期;库存快于收入上升;应收恶化;渠道库存过高 |
| durability | 多季度连续验证;订单可取消性低;留存、续约、复购或客户预算强;现金流、营运资本、CapEx 和同行口径支持持续增长 | backlog 覆盖未来几个季度;管理层指引与历史兑现率匹配;产能爬坡路径可解释;同行需求方向一致 | 单季 beat;短期供需紧缺;一次性大单;政策、补贴或事件催化尚未转成合同和现金流 | 指引依赖后置季度;放量靠降价;毛利率随放量下降;现金消耗扩大;同行口径相反 |
Evidence strength rules:
high:至少有一个 L1/L4/L5 来源直接支持,并能被财务表、订单/合同、客户行为、同行或市场预期中的至少一类交叉验证。medium:证据方向一致,但缺少直接 ASP / volume / contract / cash-flow 披露,或只覆盖未来指引而未被本期验证。low:主要来自管理层叙事、单季同比、低基数、pipeline、TAM 或 agent 推断。source_gap:关键证据缺失;不得把该驱动写成 durable conclusion。high。mixed 或降低 evidence_strength,并写明需要什么后续披露来证伪或确认。data-analysis-quality-gate,并把派生指标写入 calculation-ledger.csv 或 explicit formula note。财报分析必须把本季度事实和未来 4-8 个季度的预期变化连接起来。不能只写本季度 beat / miss,也不能把管理层指引当作已经验证的事实。
必须覆盖:
reported_vs_consensus:本季度实际收入、利润率、EPS、FCF 或核心 KPI 相对市场预期如何next_quarter_guidance:下一季度收入、利润率、EPS、FCF、CapEx 或关键经营指标指引full_year_guidance:全年指引是否上调、下调、维持或首次给出implied_bridge:按指引倒推,后续季度需要什么增长、利润率、出货、利用率或现金流路径guide_vs_consensus:指引相对 consensus 是 beat、miss、inline,还是 consensus 不可得guidance_drivers:管理层称指引由价格、量、mix、产能、成本、客户预算、供应链、FX、利率或一次性项目驱动guidance_quality:指引是否被订单、backlog、RPO、库存、客户预算、产能、同行财报或历史兑现率支持estimate_revision_impact:对 FY1 / FY2 revenue、margin、EPS、FCF、CapEx、net debt 的方向性影响guidance_risks:指引最容易失效的假设transcript_QA_delta:业绩会 Q&A 是否改变新闻稿表面结论,若 transcript 不可得必须标记 source_gap如果公司不提供正式指引,必须用 prepared remarks、Q&A、订单/产能数据、同行指引和市场预期构建 soft guidance bridge,并降低证据强度。
如果使用指引倒推后续季度路径、implied bridge 或 guide vs consensus,必须运行 data-analysis-quality-gate。如果 consensus 或必要输入不可得,相关判断必须标记 source_gap 或 calculation_gap,不能写成高置信预期差结论。
把同比和环比变化拆成经营驱动:
每个驱动必须标记为 confirmed、inferred 或 unknown。
定价和放量必须继续做可持续性测试:
必须选择至少 1 家竞争对手或最相关同行的同期财报做交叉验证:
timing_mismatch 并降低结论强度同行选择优先级:
对本期质量做分层判断:
earnings-analysis.md 必须包含:
event-delta.md 必须包含:
pre_event_setupactual_disclosuredelta_vs_expectationrevision_pathprice_reaction_qualitythesis_impactexpectation_map_updatesrequired_research_followup评分只用于强制结构化,不可替代文字判断。
| dimension | score range | meaning |
|---|---|---|
| growth_quality | 1-5 | 增长是否来自可持续经营驱动 |
| pricing_power | 1-5 | 是否具备定价权、提价权或供需主动权 |
| volume_durability | 1-5 | 放量是否有供需、产能和客户基础支撑 |
| margin_quality | 1-5 | 利润率变化是否可解释且可持续 |
| cash_conversion | 1-5 | 利润与现金流是否匹配 |
| balance_sheet_risk | 1-5 | 资产负债表是否支持继续投入 |
| guidance_credibility | 1-5 | 指引与历史兑现、订单、需求信号是否一致 |
| guidance_market_delta | -2 to +2 | 指引相对市场预期和估值隐含预期的方向与幅度 |
| peer_relative_quality | 1-5 | 相对同行的增长、定价、放量和现金流质量 |
| thesis_impact | -2 to +2 | 对原 thesis 的影响方向和强度 |
+2:核心争议被明显证实,且财务和管理层口径一致+1:方向改善,但仍需要后续季度确认0:与原 thesis 基本一致,信息增量有限-1:出现可解释但需要跟踪的瑕疵-2:核心 thesis 被削弱,或财务质量显著恶化财报分析必须明确本期证据能影响哪一层 thesis:
near_term_execution
本期实际、下一季指引、短期催化剂和价格反应。medium_term_revision
FY1 / FY2 收入、利润率、EPS、FCF、CapEx、net debt 或估值锚修正。long_term_thesis
一年以上的产业趋势、竞争位置、技术路径、利润池、商业模式或资本配置。regime_transition
短期财报信号正在改变长期 thesis,或长期 thesis 正在被短期证据证伪。如果把财报影响升级到 long_term_thesis 或 regime_transition,必须写明:
如果证据不足,必须把长期影响降级为 watch item。
财报事件不能只总结 beat / miss。必须说明本期披露改变了哪个预期变量:
如果没有可用的 pre-event consensus proxy,必须在 event-delta.md 写 source_gap,并降低 thesis impact 置信度。
价格反应只能作为 market_pricing,不能替代经营证据。管理层口径只能作为 company_claim 或 guidance,除非被财务、订单、客户、同行或外部数据验证。
L1。L5,但必须写明时间戳。claim_type、claim_text、source_speaker 和 verification_status。L6、写上游来源,并在 calculation-ledger.csv 或 explicit formula note 中记录公式、口径、期间、单位和限制。source_gap,并把 transcript 发布列为刷新触发。© byteseek, 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
Just SKILL.md in skills/earnings-report-analysis of byteseek/Mira.
Open the folder on GitHubat commit adddce7
Earnings Report Analysis 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Earnings Report Analysis this skillbyteseek/Mira | 275 | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Earnings AnalysisWind-Alice/AliceMarket | 134 | 3 repos | ~2.2k | Automated safety check: Pass | None | |
| Earnings Analysisginlix-ai/LangAlpha | 1.8k | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Healthcare Equityhh-health-AI/healthcare-equity | 101 | — | ~770 | Automated safety check: Pass | MIT | |
| Weekly Trading Planzhu1090093659/dsh-trading | 238 | — | ~2k | Automated safety check: Pass | Custom licence | |
| Financial Reportmonarchjuno/vibe-investing | 299 | — | ~1.3k | Automated safety check: Pass | MIT |
Wind-Alice/AliceMarket
Create professional equity research earnings update reports (8-12 pages, 3,000-5,000 words) analyzing quarterly results for companies already under coverage.
ginlix-ai/LangAlpha
Post-print earnings update for a covered name: beat/miss decomposition, EPS quality, transcript debate map, estimate revisions, thesis impact.
hh-health-AI/healthcare-equity
A skill your agent uses for healthcare company initiation, earnings analysis, valuation framing, thesis development, screens, portfolio research, management meetings, sell discipline, international…
zhu1090093659/dsh-trading
制定每周交易计划:把本周复盘、统一台账持仓与资金、市场消息与公告、facts/ 与知识库、假设档案(hypothesistracking / 持仓 thesis / 宏观管道状态)合成一份下周计划,逐条过六道闸门并给出双向预案与失效条件。当用户要求「制定本周/下周交易计划」「周度作战计划」「把复盘+持仓+消息+知识库合成计划」,或周末例行生成计划时调用。
monarchjuno/vibe-investing
Package investing analysis into a publishable financial-report style with institutional section flow, thesis framing, valuation context, catalysts, risks, tables, and financial charts.
sickn33/agentic-awesome-skills
Thesis-driven equity analysis from public SEC EDGAR and market data; /analyze, /score, /compare workflows with bundled Python tools (Claude Code, Cursor, Codex).
byteseek/Mira
Discover listed, pending, filed, or newly announced ETFs and create a structured candidate watchlist for ETF listing analysis.
byteseek/Mira
Run Mira's core single-equity research workflow across fundamentals, financial quality, macro context, technical pricing, events, and thesis framing.
byteseek/Mira
Analyze new, pending, or expanding ETF products as product signals, exposure maps, demand indicators, and potential asset-pricing read-throughs.
byteseek/Mira
Analyze commodity cycles, futures curves, inventories, cost curves, policy/geopolitics, positioning, and transmission into related assets.
byteseek/Mira
Gate quantitative Mira conclusions by requiring reproducible data, formulas, calculation ledgers, or explicit downgrades when numbers drive judgment.
byteseek/Mira
Map an unclear industry concept into boundaries, value chain, supply-demand mechanics, profit pools, evidence gaps, and investable candidates.
Categories
Analyze earnings releases, filings, transcripts, guidance, peer comparisons, market reaction, and thesis impact for a company reporting event. Earnings Report Analysis is an agent skill from byteseek/Mira. Analyze earnings releases, filings, transcripts, guidance, peer comparisons, market reaction, and thesis impact for a company reporting event.
Earnings Report Analysis fits situations like: tasks that involve Essays and academic help; tasks that involve Financial analysis.
Run `npx skills add byteseek/Mira --skill earnings-report-analysis -a claude-code`. Or copy the skill folder (skills/earnings-report-analysis in byteseek/Mira) into .claude/skills/earnings-report-analysis in your project. Claude Code loads it when a task matches its description.
Run `npx skills add byteseek/Mira --skill earnings-report-analysis -a codex`. Or copy the skill folder (skills/earnings-report-analysis in byteseek/Mira) into .agents/skills/earnings-report-analysis in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add byteseek/Mira --skill earnings-report-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/earnings-report-analysis, .gemini/skills/earnings-report-analysis, .github/skills/earnings-report-analysis and .opencode/skills/earnings-report-analysis in your project.
SKILL.md names no scripts, command-line tools or credentials: Earnings Report Analysis is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Earnings Report Analysis 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.
About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Earnings Report Analysis: Earnings Analysis (Wind-Alice/AliceMarket, 134 stars), Earnings Analysis (ginlix-ai/LangAlpha, 1.8k stars), Healthcare Equity (hh-health-AI/healthcare-equity, 101 stars) and Weekly Trading Plan (zhu1090093659/dsh-trading, 238 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
byteseek (a GitHub organization) maintains it in byteseek/Mira, which has 275 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 8, 2026.
Source: byteseek/Mira on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.