credit-analyzer
Skill2 starsChanged 5 months agoMITView on GitHub
Bond and credit analysis. Prices bonds, computes yield to maturity, duration, convexity, and spread-to-benchmark. Analyzes credit quality, covenant risk, and refinancing risk. Compares corporate bonds vs sovereign alternatives. Works for Turkish Eurobonds, BIST bonds, US Treasuries, and corporate bonds.
In this repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- chart-readerSkill
- dcf-thinkingSkill
- drip-optimizerSkill
- earnings-reviewerSkill
- finops-agentSkill
- gl-reconcilerSkill
- kyc-screenerSkill
- macro-calendarSkill
- macro-stressSkill
- market-researcherSkill
- ma-screenerSkill
- meeting-preparerSkill
- model-builderSkill
- monte-carloSkill
- month-end-closerSkill
- options-pricerSkill
- pdf-analyzerSkill
- pitch-builderSkill
- statement-auditorSkill
- tax-harvesterSkill
- valuation-reviewerSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 36
If ISIN or description provided, search via WebSearch for current price, coupon, maturity.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Credit Analyzer
Trigger phrases
- "Bu tahvilin YTM'si nedir?"
- "Bond pricing: [issuer] [coupon]% [maturity]"
- "Duration ve convexity hesapla"
- "Hazine bonosu vs kurumsal tahvil karşılaştır"
- "Türkiye Eurobond analizi"
- "Credit spread nedir? [şirket] tahvili"
- "Analyze bond: [ISIN or description]"
Input parameters
| Parameter | Description |
issuer | Company or sovereign name |
coupon_rate | Annual coupon rate (%) |
face_value | Par value (default: 1000) |
maturity_date | Maturity date or years to maturity |
frequency | Coupon frequency: annual/semi-annual/quarterly |
current_price | Market price (% of par, e.g. 98.5) |
settlement_date | T+2 from today (default) |
Phases
Phase 1 — Bond identification & data
If ISIN or description provided, search via WebSearch for current price, coupon, maturity. For Turkish bonds: fetch from WebSearch (e.g. "Turkey 2028 Eurobond price") or BIST bond market data. For US Treasuries: use current yield curve (fetch via WebSearch: "US Treasury yield today").
Phase 2 — Yield to Maturity (YTM)
Newton-Raphson iteration to find YTM (r) where:
Price = Σ [Coupon / (1+r)^t] + [FaceValue / (1+r)^T]For semi-annual coupons: coupon/2, r/2, double periods.
Convergence: start with r = coupon/price; iterate 10 times.
Also compute:
- Yield to Call (if callable): substitute call date and call price
- Current yield: annual coupon / current price
- Discount/premium: (Price - Par) / Par × 100%
Phase 3 — Duration & Convexity
Macaulay Duration:
D = Σ [t × PV(CFt)] / PriceModified Duration (price sensitivity to rate change):
MD = Macaulay Duration / (1 + YTM/frequency)
Price change ≈ -MD × ΔYTM × PriceConvexity (second-order correction):
Convex = Σ [t(t+1) × PV(CFt)] / [Price × (1+r)²]Combined price change for ΔYTM:
ΔP/P ≈ -MD × ΔYTM + 0.5 × Convexity × ΔYTM²Present in table:
| Rate change | Duration effect | Convexity correction | Net price change |
| -200bps | |||
| -100bps | |||
| +100bps | |||
| +200bps |
Phase 4 — Credit spread analysis
Spread to benchmark:
Credit spread = YTM(bond) - YTM(benchmark)Benchmark: same-maturity government bond (Turkey GB for Turkish issuers, US Treasury for USD bonds).
Fetch benchmark yield via WebSearch.
Spread interpretation:
- < 50bps: investment grade (AAA-AA)
- 50-150bps: investment grade (A-BBB)
- 150-400bps: high yield (BB)
400bps: distressed / CCC territory
Z-spread (vs swap curve): if swap rates available, compute parallel shift to discount curve.
Phase 5 — Credit quality assessment
Research via WebSearch:
- Credit rating: Moody's / S&P / Fitch (or implied from spread)
- Rating trend: stable / positive / negative outlook
- Key credit metrics:
- Net debt / EBITDA (< 3× = investment grade)
- Interest coverage (EBITDA / Interest > 3× = safe)
- Free cash flow / Total debt > 10% = positive
- Recent rating actions or watch-list placement
Covenant check (if prospectus available):
- Change of control put
- Debt incurrence covenant
- Dividend restriction
- Cross-default provision
Phase 6 — Refinancing risk
- Maturity wall: what debt matures in next 2-3 years?
- Available credit facilities / revolving credit
- Market access: issuer has issued recently? Spread trend tightening or widening?
- For sovereigns: IMF program, FX reserves, current account deficit
Phase 7 — Comparison vs alternatives
Build comparison table for similar maturity:
| Instrument | Yield | Duration | Credit rating | Liquidity |
| This bond | ||||
| Govt benchmark | ||||
| Sector peer bond | ||||
| TRY deposit (if TRY bond) |
Breakeven analysis: at what spread widening does the government bond outperform?
Breakeven = current spread - coupon advantage / modified durationPhase 8 — Output
Write output/credit-<issuer>-<YYYYMMDD>.md:
# Credit Analysis: <Issuer> <Coupon>% <Maturity>
## Bond Summary
## Pricing & Yield Metrics
## Duration & Rate Sensitivity
## Credit Spread Analysis
## Credit Quality Assessment
## Covenant Highlights
## Refinancing Risk
## Comparison vs Alternatives
## Recommendation
## AssumptionsDisclaimer: Bond prices fluctuate. Credit ratings can change. Illiquid bonds may have wide bid-ask spreads. Not investment advice.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

